Lucene.Net核心类简介,创建索引,搜索,Lucene高亮组建演示,Rss获得最新帖子,只索引帖子的有意义部分,在AddDocument之前先移除旧有文档.

 private ILog logger = LogManager.GetLogger(typeof(text_创建索引));
protected void Page_Load(object sender, EventArgs e)
{

}
protected void Button1_Click(object sender, EventArgs e)
{
// 1、对数据进行索引
string indexPath = "c:/ceshi";
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NativeFSLockFactory());
bool isUpdate = IndexReader.IndexExists(directory);
if (isUpdate)
{
//如果索引目录被锁定（比如索引过程中程序异常退出），则首先解锁
if (IndexWriter.IsLocked(directory))
{
IndexWriter.Unlock(directory);
}
}
IndexWriter writer = new IndexWriter(directory, new PanGuAnalyzer(), !isUpdate, Lucene.Net.Index.IndexWriter.MaxFieldLength.UNLIMITED);
WebClient wc = new WebClient();
//wc.Encoding = Encoding.UTF8;//否则可能会有乱码问题！！
int maxId = GetMaxId();
for (int i = 1; i < maxId; i++)
{
string url = "http://www.discuz.net/thread-" + i + "-1-1.html";
string html = wc.DownloadString(url);
HTMLDocumentClass doc = new HTMLDocumentClass();
doc.designMode = "on"; //不让解析引擎去尝试运行javascript
doc.IHTMLDocument2_write(html);
string title = doc.title;
string body = doc.body.innerText;//去掉标签
//为避免重复索引，所以先删除number=i的记录，再重新添加.
writer.DeleteDocuments(new Term("number", i.ToString()));
Document document = new Document();
//只有对需要全文检索的字段才ANALYZED
document.Add(new Field("number", i.ToString(), Field.Store.YES, Field.Index.NOT_ANALYZED));
document.Add(new Field("title", title, Field.Store.YES, Field.Index.ANALYZED, Lucene.Net.Documents.Field.TermVector.WITH_POSITIONS_OFFSETS));
document.Add(new Field("body", body, Field.Store.YES, Field.Index.ANALYZED, Lucene.Net.Documents.Field.TermVector.WITH_POSITIONS_OFFSETS));
writer.AddDocument(document);
logger.Debug(("索引" + i + "完毕"));
}

writer.Close();
directory.Close();//不要忘了Close，否则索引结果搜不到
logger.Debug("全部索引完毕！");

}
protected void Button2_Click(object sender, EventArgs e)
{
string indexPath = "c:/ceshi";
string kw = TextBox1.Text;
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NoLockFactory());
IndexReader reader = IndexReader.Open(directory, true);
IndexSearcher searcher = new IndexSearcher(reader);
PhraseQuery query = new PhraseQuery();
foreach (string word in CommonHelper.SplitWord(TextBox1.Text))//先用空格，让用户去分词，空格分隔的就是词“计算机   专业”
{
query.Add(new Term("body", word));
}
query.SetSlop(100);
TopScoreDocCollector collector = TopScoreDocCollector.create(1000, true);
searcher.Search(query, null, collector);
ScoreDoc[] docs = collector.TopDocs(0, collector.GetTotalHits()).scoreDocs;
List<SearchResult> listResult = new List<SearchResult>();

for (int i = 0; i < docs.Length; i++)
{
//取到文档的编号（主键,这个是Luncene.net分配的）
int docId = docs[i].doc;
//检索结果中只有文档的id,如果要取Document,则需要Doc再去取
//降低内容占用
Document doc = searcher.Doc(docId);

string number = doc.Get("number");
string title = doc.Get("title");
string body = doc.Get("body");
SearchResult result = new SearchResult();
result.Number = number;
result.Title = title;
//高亮--------------------------------------
//创建HTMLFormatter,参数为高亮单词的前后缀
PanGu.HighLight.SimpleHTMLFormatter simpleHTMLFormatter =
new PanGu.HighLight.SimpleHTMLFormatter("<font color=\"red\">", "</font>");
//创建Highlighter ，输入HTMLFormatter 和盘古分词对象Semgent
PanGu.HighLight.Highlighter highlighter =
new PanGu.HighLight.Highlighter(simpleHTMLFormatter,
new Segment());
//设置每个摘要段的字符数
highlighter.FragmentSize = 50;
//获取最匹配的摘要段
String bodyPreview = highlighter.GetBestFragment(TextBox1.Text, body);
result.BodyPreview = bodyPreview;
Response.Write(number + "<br/>");
Response.Write(title + "<br/>");
Response.Write("<hr/>");
listResult.Add(result);
}
Repeater1.DataSource = listResult;
Repeater1.DataBind();

}
private int GetMaxId()
{
XDocument xdoc = XDocument.Load("http://www.discuz.net/forum.php?mod=rss&fid=21&auth=0");
XElement channel = xdoc.Root.Element("channel");
XElement firstItem = channel.Elements("item").First();
XElement link = firstItem.Element("link");
Match match = Regex.Match(link.Value, @"viewthread&tid=(\d+)\\");
string id = match.Groups[1].Value;
return Convert.ToInt32(id);

}

 public class CommonHelper
{
public static string[] SplitWord(string str)
{
List<string> list = new List<string>();
Analyzer analyzer = new PanGuAnalyzer();
// Analyzer analyzer = new CJKTokenizer();
// Analyzer analyzer = new StandardAnalyzer();
TokenStream tokenStream = analyzer.TokenStream("", new StringReader(str));
Lucene.Net.Analysis.Token token = null;
while ((token = tokenStream.Next()) != null)
{
list.Add(token.TermText() );
}
return list.ToArray();
}
}

 public class SearchResult
{
public string Number { get; set; }
public string Title { get; set; }
public string BodyPreview { get;set;}
}