public SearchResult[] Search(string query)
{
Hits hits = _doSearch(query);
List<SearchResult> results = new List<SearchResult>();
for (int i = 0; i < hits.Length(); i++)
{
Document doc = hits.Doc(i);
string contents = doc.Get("contents");
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>");
SimpleFragmenter fragmenter = new SimpleFragmenter(_fragmentSize);
Highlighter hiliter = new Highlighter(formatter, new QueryScorer(QueryParser.Parse(query, "contents", _analyzer)));
hiliter.SetTextFragmenter(fragmenter);
int numfragments = contents.Length / fragmenter.GetFragmentSize() + 1;
TokenStream tokenstream = _analyzer.TokenStream("contents", new StringReader(contents));
TextFragment[] frags = hiliter.GetBestTextFragments(tokenstream, contents, false, numfragments);
SearchResult sr = new SearchResult(doc, _analyzer, query, _fragmentSize);
foreach (TextFragment frag in frags)
{
if (frag.GetScore() > 0)
sr.AddFragment(frag.ToString());
}
results.Add(sr);
}
return results.ToArray();
}
public static string GetOriginalHighlightedContents(SearchResult sr)
{
StringBuilder result = new StringBuilder("<html><meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\"><style>.highlight{background:yellow;}</style><body><font face=Arial size=5>");
string contents = sr.GetDocContents();
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>");
SimpleFragmenter fragmenter = new SimpleFragmenter(sr.FragmentSize);
Highlighter hiliter = new Highlighter(formatter, new QueryScorer(sr.QueryParser.Parse(sr.Query)));
hiliter.SetTextFragmenter(fragmenter);
int numfragments = contents.Length / fragmenter.GetFragmentSize() + 1;
TokenStream tokenstream = sr.Analyzer.TokenStream("contents", new StringReader(contents));
result.Append(hiliter.GetBestFragments(tokenstream, contents, numfragments, "..."));
result.Append("</font></body></html>");
result.Replace("\n", "<br/>");
return result.ToString();
}
public static string GetHilitedContentsWithoutHeaders(SearchResult sr)
{
StringBuilder result = new StringBuilder("<font face=Arial size=5>");
string contents = sr.GetDocContents();
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>");
SimpleFragmenter fragmenter = new SimpleFragmenter(sr.FragmentSize);
Highlighter hiliter = new Highlighter(formatter, new QueryScorer(sr.QueryParser.Parse(sr.Query)));
hiliter.SetTextFragmenter(fragmenter);
int numfragments = contents.Length / fragmenter.GetFragmentSize() + 1;
TokenStream tokenstream = sr.Analyzer.TokenStream("contents", new StringReader(contents));
result.Append(hiliter.GetBestFragments(tokenstream, contents, numfragments, "..."));
result.Append("</font>");
result.Replace("\n", "<br/>");
return result.ToString();
}
public static void Highlight(Document d, string query, Analyzer analyzer)
{
string contents = d.Get("contents");
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\"><b>", "</b></span>");
//SpanGradientFormatter formatter = new SpanGradientFormatter(10.0f, null, null, "#F1FD9F", "#EFF413");
//SimpleHTMLEncoder encoder = new SimpleHTMLEncoder();
SimpleFragmenter fragmenter = new SimpleFragmenter(250);
Highlighter hiliter = new Highlighter(formatter, new QueryScorer(QueryParser.Parse(query, "contents", analyzer)));
hiliter.SetTextFragmenter(fragmenter);
int numfragments = contents.Length / fragmenter.GetFragmentSize() + 1;// +1 ensures its never zero. More than the required number of fragments dont harm.
StringBuilder result = new StringBuilder("<html><meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\"><style>.highlight{background:yellow;}</style><head><title>Search Results - ");
result.Append(d.Get("filename"));
result.Append("</title></head><body><font face=Arial size=5>");
TokenStream tokenstream = analyzer.TokenStream("contents", new System.IO.StringReader(contents));
TextFragment[] frags = hiliter.GetBestTextFragments(tokenstream, contents, false, numfragments);
foreach (TextFragment frag in frags)
{
if (frag.GetScore() > 0)
{
result.Append(frag.ToString() + "<br/><hr/><br/>");
}
}
string contentspath = System.IO.Path.Combine(System.Windows.Forms.Application.StartupPath, "contents.html");
result.Append("</font><a target=_self href=\"file:///");
result.Append(contentspath);
result.Append("\">View Original Document...</a>");
result.Append("</body></html>");
result.Replace("\n", "<br/>");
string resultspath = System.IO.Path.Combine(System.Windows.Forms.Application.StartupPath, "results.html");
System.IO.File.WriteAllText(resultspath, result.ToString());
//webBrowser1.Url = new Uri("file:///" + resultspath);
Highlighter hiliter2 = new Highlighter(formatter, new QueryScorer(QueryParser.Parse(query, "contents", analyzer)));
hiliter2.SetTextFragmenter(fragmenter);
TokenStream tokstr = analyzer.TokenStream(new System.IO.StringReader(contents));
StringBuilder htmlcontents = new StringBuilder("<html><meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\"><style>.highlight{background:yellow;}</style><body><font face=Arial size=5>");
htmlcontents.Append(hiliter2.GetBestFragments(tokstr, contents, numfragments, "..."));
htmlcontents.Append("</font></body></html>");
htmlcontents.Replace("\n", "<br/>");
System.IO.File.WriteAllText(contentspath, htmlcontents.ToString());
}
public static SearchResult GetFastSearchResultFragments(ref SearchResult sr)
{
Document doc = sr.Document;
string contents = doc.Get("contents");
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">", "</span>");
SimpleFragmenter fragmenter = new SimpleFragmenter(sr.FragmentSize);
Highlighter hiliter = new Highlighter(formatter, new QueryScorer(sr.QueryParser.Parse(sr.Query)));
hiliter.SetTextFragmenter(fragmenter);
int numfragments = contents.Length / fragmenter.GetFragmentSize() + 1;
TokenStream tokenstream = sr.Analyzer.TokenStream("contents", new StringReader(contents));
TextFragment[] frags = hiliter.GetBestTextFragments(tokenstream, contents, false, numfragments);
//SearchResult sr = new SearchResult(doc, _analyzer, query, _fragmentSize);
foreach (TextFragment frag in frags)
{
if (frag.GetScore() > 0)
sr.AddFragment(frag.ToString());
}
return sr;
}
private void Search()
{
try
{
SearchProgressBar.Maximum = 11;
ProgressLabel.Text = "Progress: Initialize Search ...";
Searcher searcher = new IndexSearcher(@"Canon\index");
Analyzer analyzer = new StandardAnalyzer();
ArrayList resultList = new ArrayList();
System.IO.StreamReader in_Renamed = new System.IO.StreamReader(new System.IO.StreamReader(System.Console.OpenStandardInput(), System.Text.Encoding.Default).BaseStream, new System.IO.StreamReader(System.Console.OpenStandardInput(), System.Text.Encoding.Default).CurrentEncoding);
String line = QueryInputBox.Text;
if (line.Length == - 1)
return;
ProgressLabel.Text = "Progress: Parsing Query ...";
Query query = QueryParser.Parse(line, "contents", analyzer);
//int[] ix = qtm.GetTermFrequencies();
Hits hits = searcher.Search(query);
SearchProgressBar.Increment(1);
ProgressLabel.Text = "Progress: Searched. Analyzing results ...";
//QueryHighlightExtractor highlighter = new QueryHighlightExtractor(query, new WhitespaceAnalyzer(), "<B>", "</B>");
Highlighter highlighter = new Highlighter(new QueryScorer(query));
highlighter.SetTextFragmenter(new SimpleFragmenter(80));
int maxNumFragmentsRequired = 1;
//int HITS_PER_PAGE = 10;
for (int i = 0; i < 10; i++)
{
SearchProgressBar.Increment(1);
ProgressLabel.Text = "Progress: Analyzing hit " + (i+1).ToString();
// get the document from index
Document doc = hits.Doc(i);
//SegmentReader ir = new SegmentReader();
//Lucene.Net.Index.TermFreqVector tfv =
//tfv.GetTermFrequencies
string score = hits.Score(i).ToString();
//Box += "Hit no. " + i + " scored: " + score + " occ: " + /*highlighter.tokenFrequency */ " best fragment: \n";
ResultSet a = new ResultSet();
a.BookName = doc.Get("path").Replace(@"c:\cscd\temp\","");
a.Score = hits.Score(i);
a.numberOfHits = hits.Length();
// get the document filename
// we can't get the text from the index
//because we didn't store it there
//so get it from archive
string path = doc.Get("path");
string name = GetInternalName(path);
PaliReaderUtils.AalekhDecoder.UnzipFromZipLibrary(name);
path = System.IO.Directory.GetCurrentDirectory() + @"\Work\" + name + ".htm";
string plainText = "";
//load text from zip archive temporarily
using (StreamReader sr = new StreamReader(path, System.Text.Encoding.Default))
{
plainText = parseHtml(sr.ReadToEnd());
}
//-------------------------------Highlighter Code 1.4
TokenStream tokenStream = analyzer.TokenStream(new StringReader(plainText));
a.textFragment = highlighter.GetBestFragments(tokenStream, plainText, maxNumFragmentsRequired, "...");
if(File.Exists(path))
File.Delete(path);
//-------------------------------
resultList.Add(a);
}
SearchProgressBar.Value = 0;
searcher.Close();
ssr = new ShowSearchResults(/*Box*/resultList);
//this.Hide();
ssr.OpenBookEvent += new ShowSearchResults.OpenBook(this.TriggerOpenBook);
ssr.Closing += new System.ComponentModel.CancelEventHandler(this.Closing_ResultWindow);
this.Hide();
ssr.ShowDialog();
}
catch (System.Exception e)
{
MessageBox.Show(" caught a " + e.GetType() + "\n with message: " + e.Message);
}
}