关于搜索引擎的一些源代码
//第一个版本应该保存body和title,搜索结果形成超链接,不显示正文。
protected void Button1_Click(object sender, EventArgs e)
{
string indexPath = "c:/index";//设置索引文件保存的路径
//Directory表示索引文件(Lucene用来保存用户扔过来的数据的地方)保存的地方
//是抽象类,两个子类FSDirectory(文件中)、RAMDire ctory (内存中)。indexpath表示索引的文件夹路径
FSDirectory directory = FSDirectory.Open(new DirectoryInfo(indexPath), new NativeFSLockFactory());
//IndexReader的静态方法bool IndexExists(Directory directory)判断目录directory是否是一个索引目录。
bool isUpdate = IndexReader.IndexExists(directory);
if (isUpdate)//假如该目录存在
{
//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))
{
//在对目录写之前会先把目录锁定。两个IndexWriter没法同时写一个索引文件。IndexWriter在进行写操作的时候会自动加锁,close的时候会自动解锁
IndexWriter.Unlock(directory);
}
}
//IndexReader对索引进行读取的类,对IndexWriter进行写的类
IndexWriter writer = new IndexWriter(directory, new PanGuAnalyzer(), !isUpdate, Lucene.Net.Index.IndexWriter.MaxFieldLength.UNLIMITED);
WebClient wc = new WebClient();
wc.Encoding = Encoding.UTF8;//否则下载的是乱码
//todo:读取rss,获得第一个item中的链接的编号部分就是最大的帖子编号
int maxId = GetMaxId();
for (int i = 1; i <= maxId; i++)
{
//依次获得地址
string url = "-" + i + ".aspx";
//根据地址依次将对应的该网页下载下来
string html = wc.DownloadString(url);
//将各个文档解析
HTMLDocumentClass doc = new HTMLDocumentClass();
doc.designMode = "on"; //不让解析引擎去尝试运行javascript
doc.IHTMLDocument2_write(html);
doc.close();
string title = doc.title;
有没有什么网站分享源码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.NOT_ANALYZED));
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:/index";
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();
//todo:把用户输入的关键词进行拆词
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.Add(new Term("body","计算机"));
//query.Add(new Term("body", "专业"));
query.SetSlop(100);
TopScoreDocCollector collector = ate(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++)
{
int docId = docs[i].doc;//取到文档的编号(主键,这个是Lucene 分配的)
//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);//根据idDocument
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;
result.BodyPreview = Preview(body,TextBox1.Text);
listResult.Add(result);
}
repeaterResult.DataSource = listResult;
repeaterResult.DataBind();
}
private static string Preview(string body,string keyword)
{
//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 = 100;
//获取最匹配的摘要段
String bodyPreview = highlighter.GetBestFragment(keyword, body);
return bodyPreview;
}
private int GetMaxId()
{
XDocument xdoc = XDocument.Load("");
XElement channel = xdoc.Root.Element("channel");
XElement firstItem = channel.Elements("item").First();
XElement link = firstItem.Element("link");
Match match =
Regex.Match(link.Value, @"showtopic-(\d+)\.aspx");
string id =match.Groups[1].Value;
版权声明:本站内容均来自互联网,仅供演示用,请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198,我们将在24小时内删除。
发表评论