public string Search(string strQuery)
{
string result = string.Empty;
Lucene.Net.Index.IndexReader reader = Lucene.Net.Index.IndexReader.Open(Server.MapPath(System.Configuration.ConfigurationManager.AppSettings["IndexingArticle"]));
Lucene.Net.QueryParsers.QueryParser parser = new Lucene.Net.QueryParsers.QueryParser("ArticleDetail", new Lucene.Net.Analysis.Standard.StandardAnalyzer());
Lucene.Net.Search.Query query = parser.Parse(strQuery);
Lucene.Net.Search.IndexSearcher searcher = new Lucene.Net.Search.IndexSearcher(reader);
Lucene.Net.Search.Hits hits = searcher.Search(query);
Lucene.Net.Highlight.QueryScorer score = new Lucene.Net.Highlight.QueryScorer(query);
Lucene.Net.Highlight.SimpleHTMLFormatter formater = new Lucene.Net.Highlight.SimpleHTMLFormatter("<span class='Highlight'>", "</span>");
Lucene.Net.Highlight.Highlighter highlighter = new Lucene.Net.Highlight.Highlighter(formater, score);
result += "<div align='right' style='background-color:#F0F7F9; padding-right:15px' height='30px'><font style='FONT-WEIGHT: bold; FONT-SIZE: 10pt; COLOR: #005482; FONT-FAMILY: arial'>Kết quả tìm thấy : " + hits.Length() + " </font></div>";
result += "<div style='padding: 10px 10px 10px 10px;'>";
for (int i = 0; i < hits.Length(); i++)
{
string id = hits.Doc(i).Get("ArticleId");
string title = hits.Doc(i).Get("ArticleTitle");
string detail = hits.Doc(i).Get("ArticleDetail");
Lucene.Net.Analysis.TokenStream ts = (new Lucene.Net.Analysis.Standard.StandardAnalyzer()).TokenStream("ArticleDetail", new System.IO.StringReader(detail));
result += string.Format("<div align='left'><font style='FONT-WEIGHT: bold; FONT-SIZE: 10pt; COLOR: #5b5b5b; FONT-FAMILY: arial'><a href='/?ArticleId={0}'>{1}</a></font>", id, title);
result += string.Format("<div align='left'><font style='FONT-SIZE: 9pt' face='Arial' color='#005482'>...{0}...</font></div></div></br>", highlighter.GetBestFragment(ts, detail));
}
result += "</div>";
reader.Close();
return(result);
}
public string SearchAndPaging(string strQuery, string index)
{
string result = string.Empty;
try
{
List <SearchArticle> searchArticleList = new List <SearchArticle>();
PSCPortal.CMS.ArticleCollection ArticleList = ArticleCollection.GetArticleCollectionPublish();
string nameSub = Libs.Ultility.GetSubDomain() == string.Empty ? "HomePage" : Libs.Ultility.GetSubDomain();
SubDomain subDomain = PSCPortal.Engine.SubDomain.GetSubByName(nameSub);
PageCollection pagesBelongTo = subDomain.GetPagesBelongTo();
string strId = string.Empty;
foreach (var page in pagesBelongTo)
{
foreach (var ar in ArticleList.Where(ar => ar.PageId == page.Id))
{
strId += ar.Id + " OR ";
}
if (strId.Length > 0)
{
strId = strId.Remove(strId.Length - 3, 3);
}
}
int pageIndex = Int32.Parse(index);
string strSearch = " ArticleDetail:(" + strQuery + ") AND ArticleId:" + "( " + strId + " )";
Lucene.Net.Index.IndexReader reader = Lucene.Net.Index.IndexReader.Open(Server.MapPath(System.Configuration.ConfigurationManager.AppSettings["IndexingArticle"]));
Lucene.Net.QueryParsers.QueryParser parser = new Lucene.Net.QueryParsers.QueryParser("ArticleDetail", new Lucene.Net.Analysis.Standard.StandardAnalyzer());
Lucene.Net.Search.Query query = parser.Parse(strSearch);
Lucene.Net.Search.IndexSearcher searcher = new Lucene.Net.Search.IndexSearcher(reader);
Lucene.Net.Search.Hits hits = searcher.Search(query);
Lucene.Net.Highlight.QueryScorer score = new Lucene.Net.Highlight.QueryScorer(query);
Lucene.Net.Highlight.SimpleHTMLFormatter formater = new Lucene.Net.Highlight.SimpleHTMLFormatter("<span class='Highlight'>", "</span>");
Lucene.Net.Highlight.Highlighter highlighter = new Lucene.Net.Highlight.Highlighter(formater, score);
result += hits.Length() + "_" + "<div class='blog_news'><div class='topic_news_title1'><div class='topic_news_title'><a href='#'>Kết quả tìm thấy: " + hits.Length() + "</a></div></div>";
result += "<div class='ct_topic_l'><div class='ct_topic_r1'>";
for (int i = pageIndex * 20 - 20; i < pageIndex * 20 && i < hits.Length(); i++)
{
string detail = hits.Doc(i).Get("ArticleDetail");
Lucene.Net.Analysis.TokenStream ts = (new Lucene.Net.Analysis.Standard.StandardAnalyzer()).TokenStream("ArticleDetail", new System.IO.StringReader(detail));
SearchArticle searchArticle = new SearchArticle();
searchArticle.Id = hits.Doc(i).Get("ArticleId");;
searchArticle.Title = hits.Doc(i).Get("ArticleTitle");
searchArticle.Highligth = highlighter.GetBestFragment(ts, detail);
searchArticleList.Add(searchArticle);
}
reader.Close();
JavaScriptSerializer serializer = new JavaScriptSerializer();
Dictionary <string, object> resultDic = new Dictionary <string, object>();
resultDic["Count"] = hits.Length();
resultDic["Data"] = searchArticleList;
result = serializer.Serialize(resultDic);
}
catch (Exception e)
{
}
return(result);
}
public virtual void TestMaxSizeHighlightTruncates()
{
System.String goodWord = "goodtoken";
System.String[] stopWords = new System.String[]{"stoppedtoken"};
TermQuery query = new TermQuery(new Term("data", goodWord));
SimpleHTMLFormatter fm = new SimpleHTMLFormatter();
Highlighter hg = new Highlighter(fm, new QueryScorer(query));
hg.SetTextFragmenter(new NullFragmenter());
System.String match = null;
System.Text.StringBuilder sb = new System.Text.StringBuilder();
sb.Append(goodWord);
for (int i = 0; i < 10000; i++)
{
sb.Append(" ");
sb.Append(stopWords[0]);
}
hg.SetMaxDocBytesToAnalyze(100);
match = hg.GetBestFragment(new StandardAnalyzer(stopWords), "data", sb.ToString());
Assert.IsTrue(match.Length < hg.GetMaxDocBytesToAnalyze(), "Matched text should be no more than 100 chars in length ");
//add another tokenized word to the overrall length - but set way beyond
//the length of text under consideration (after a large slug of stop words + whitespace)
sb.Append(" ");
sb.Append(goodWord);
match = hg.GetBestFragment(new StandardAnalyzer(stopWords), "data", sb.ToString());
Assert.IsTrue(match.Length < hg.GetMaxDocBytesToAnalyze(), "Matched text should be no more than 100 chars in length ");
}
public IEnumerable<Content> Search(string keyword, int page, int pageSize, out int totals)
{
lock (locker)
{
List<Content> result = new List<Content>();
IndexReader reader = IndexReader.Open(DBNLConfigurationManager.LuceneElement.IndexingFolder);
IndexSearcher searcher = new IndexSearcher(reader);
TopDocCollector collector = new TopDocCollector((page + 1) * pageSize);
PhraseQuery pquery = new PhraseQuery();
BooleanQuery myquery = new BooleanQuery();
PhraseQuery q2 = new PhraseQuery();
//grab the search terms from the query string
string[] str = keyword.Split(' ');
//build the query
foreach (string word in str)
{
//brand is the field I'm searching in
q2.Add(new Term("content", word.ToLower()));
}
//finally, add it to the BooleanQuery object
myquery.Add(q2, BooleanClause.Occur.MUST);
//foreach (string srt in keyword.Split(new char[] {' '}))
//{
// pquery.Add(new Term("content", srt.ToLower()));
//}
//pquery.Add(q2, BooleanClause.Occur.MUST);
TermQuery query = new TermQuery(new Term("content", keyword));
// TopDocs topDocs = searcher.Search(query, collector);
//searcher.Search(query, collector);
QueryParser qp = new QueryParser("content", new StandardAnalyzer());
//Contains a phrase such as "this is a phrase"
Query q = qp.Parse(keyword);
//Hits hits = searcher.Search(q);
//Hits hits = searcher.Search(query);
Hits hits = searcher.Search(myquery);
//ScoreDoc[] hits = collector.TopDocs().scoreDocs;
totals = hits.Length();
Lucene.Net.Highlight.Formatter formatter = new Lucene.Net.Highlight.SimpleHTMLFormatter(
"<span class=\"Highlight\">",
"</span>");
Lucene.Net.Highlight.SimpleFragmenter fragmenter = new Lucene.Net.Highlight.SimpleFragmenter(400);
Lucene.Net.Highlight.QueryScorer scorer = new Lucene.Net.Highlight.QueryScorer(myquery);
Lucene.Net.Highlight.Highlighter highlighter = new Lucene.Net.Highlight.Highlighter(formatter, scorer);
highlighter.SetTextFragmenter(fragmenter);
for (int i = (page - 1) * pageSize; i < Math.Min(page * pageSize, hits.Length()); i++)
{
Document doc = hits.Doc(i);
string raw_text = doc.Get("content");
Lucene.Net.Analysis.TokenStream stream = analyzer.TokenStream("", new System.IO.StringReader(raw_text));
string highlighted_text = highlighter.GetBestFragments(stream, raw_text, 1, "...").Replace("'", "''");
if (highlighted_text == "") // someties the highlighter fails to emit text...
{
highlighted_text = raw_text.Replace("'", "''");
}
if (highlighted_text.Length > 500)
{
highlighted_text = highlighted_text.Substring(0, 500);
}
Content content = new ContentService().GetItem(int.Parse(doc.Get("id")));
content.HighlightText = highlighted_text;
result.Add(content);
}
reader.Close();
searcher.Close();
return result.AsEnumerable();
}
}
public string Query(string keyword)
{
Lucene.Net.QueryParsers.QueryParser parser = new Lucene.Net.QueryParsers.QueryParser("text", analyzer);
Lucene.Net.Search.Query query = null;
try
{
if (string.IsNullOrEmpty(keyword))
{
throw new Exception("keywork is empty");
}
query = parser.Parse(keyword);
}
catch (Exception e)
{
}
lock (locker)
{
Lucene.Net.Search.Hits hits = null;
try
{
if (searcher == null)
{
searcher = new Lucene.Net.Search.IndexSearcher(DBNLConfigurationManager.LuceneElement.IndexingFolder);
}
hits = searcher.Search(query);
}
catch (Exception e)
{
}
for (int i = 0; i < hits.Length(); i++)
{
Lucene.Net.Documents.Document doc = hits.Doc(i);
}
Lucene.Net.Highlight.Formatter formatter = new Lucene.Net.Highlight.SimpleHTMLFormatter(
"<span style=\"background:yellow;color:red;\">",
"</span>");
Lucene.Net.Highlight.SimpleFragmenter fragmenter = new Lucene.Net.Highlight.SimpleFragmenter(400);
Lucene.Net.Highlight.QueryScorer scorer = new Lucene.Net.Highlight.QueryScorer(query);
Lucene.Net.Highlight.Highlighter highlighter = new Lucene.Net.Highlight.Highlighter(formatter, scorer);
highlighter.SetTextFragmenter(fragmenter);
StringBuilder sb = new StringBuilder();
string guid = Guid.NewGuid().ToString().Replace("-", "");
Dictionary<string, int> dict_already_seen_ids = new Dictionary<string, int>();
// insert the search results into a temp table which we will join with what's in the database
for (int i = 0; i < hits.Length(); i++)
{
if (dict_already_seen_ids.Count < 100)
{
Lucene.Net.Documents.Document doc = hits.Doc(i);
string id = doc.Get("id");
if (!dict_already_seen_ids.ContainsKey(id))
{
dict_already_seen_ids[id] = 1;
string raw_text =doc.Get("raw_text");
Lucene.Net.Analysis.TokenStream stream = analyzer.TokenStream("", new System.IO.StringReader(raw_text));
string highlighted_text = highlighter.GetBestFragments(stream, raw_text, 1, "...").Replace("'", "''");
if (highlighted_text == "") // someties the highlighter fails to emit text...
{
highlighted_text = raw_text.Replace("'", "''");
}
if (highlighted_text.Length > 3000)
{
highlighted_text = highlighted_text.Substring(0, 3000);
}
sb.Append(highlighted_text);
sb.Append("'");
sb.Append(")\n");
}
}
else
{
break;
}
}
return sb.ToString();
}
}
public SearchModel Search(string searchText)
{
var result = new SearchModel();
if (string.IsNullOrEmpty(searchText))
{
result.Message = "Įveskite paieškos užklausą.";
return(result);
}
var stemmedSearchText = new LithuanianStemmer().Stem(searchText.Trim());
if (string.IsNullOrEmpty(stemmedSearchText))
{
result.Message = "Įveskite paieškos užklausą.";
return(result);
}
Lucene.Net.Search.Hits hits = null;
try
{
if (char.IsLetter(stemmedSearchText[stemmedSearchText.Length - 1]))
{
stemmedSearchText += "*";
}
query = parser.Parse(stemmedSearchText);
if (searcher == null)
{
searcher = new Lucene.Net.Search.IndexSearcher(CustomAppSettings.SearchIndexFolder);
}
hits = searcher.Search(query);
}
catch (Exception e)
{
result.Message = "Paieška nepavyko. Pataisykite užklausą. Klaidos pranešimas: " + e.Message;
return(result);
}
Lucene.Net.Highlight.Formatter formatter = new Lucene.Net.Highlight.SimpleHTMLFormatter(
"<span class=\"highlightResult\">",
"</span>");
var fragmenter = new Lucene.Net.Highlight.SimpleFragmenter(100);
var scorer = new Lucene.Net.Highlight.QueryScorer(searcher.Rewrite(query));
var highlighter = new Lucene.Net.Highlight.Highlighter(formatter, scorer);
highlighter.SetTextFragmenter(fragmenter);
Dictionary <string, int> dict_already_seen_ids = new Dictionary <string, int>();
var list = new List <SearchIndexModel>();
// insert the search results into a temp table which we will join with what's in the database
for (int i = 0; i < hits.Length(); i++)
{
if (dict_already_seen_ids.Count < 100)
{
Lucene.Net.Documents.Document doc = hits.Doc(i);
string id = doc.Get("id");
if (!dict_already_seen_ids.ContainsKey(id))
{
dict_already_seen_ids[id] = 1;
var model = new SearchIndexModel();
model.Id = id;
model.Score = hits.Score(i);
model.Subject = doc.Get("subject");
model.Type = (EntryTypes)Enum.Parse(typeof(EntryTypes), doc.Get("type"));
string raw_text = HttpUtility.HtmlEncode(doc.Get("raw_text"));
//string raw_text = doc.Get("raw_text");
Lucene.Net.Analysis.TokenStream stream = analyzer.TokenStream("text",
new System.IO.StringReader(
raw_text));
string highlighted_text = highlighter.GetBestFragments(stream, raw_text, 3, "...").Replace("'",
"''");
if (highlighted_text == "") // someties the highlighter fails to emit text...
{
highlighted_text = raw_text.Replace("'", "''");
}
if (highlighted_text.Length > 3000)
{
highlighted_text = highlighted_text.Substring(0, 3000);
}
model.HighlightedText = highlighted_text;
list.Add(model);
}
}
else
{
break;
}
}
result.List = list;
result.SearchPhrase = searchText;
if (list.Count == 0)
{
result.Message = string.Format("Įrašų pagal užklausą '{0}' nerasta. Patikslinkite paieškos duomenis.", searchText);
}
return(result);
}
