Lucene HTMLFormatter skipping last character
- by Midhat
I have this simple Lucene search code (Modified from http://www.lucenetutorial.com/lucene-in-5-minutes.html)
class Program
{
static void Main(string[] args)
{
StandardAnalyzer analyzer = new StandardAnalyzer();
Directory index = new RAMDirectory();
IndexWriter w = new IndexWriter(index, analyzer, true,
IndexWriter.MaxFieldLength.UNLIMITED);
addDoc(w, "Table 1 <table> content </table>");
addDoc(w, "Table 2");
addDoc(w, "<table> content </table>");
addDoc(w, "The Art of Computer Science");
w.Close();
String querystr = "table";
Query q = new QueryParser("title", analyzer).Parse(querystr);
Lucene.Net.Search.IndexSearcher searcher = new
Lucene.Net.Search.IndexSearcher(index);
Hits hitsFound = searcher.Search(q);
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("*", "*");
Highlighter highlighter = null;
highlighter = new Highlighter(formatter, new QueryScorer(searcher.Rewrite(q)));
for (int i = 0; i < hitsFound.Length(); i++)
{
Console.WriteLine(highlighter.GetBestFragment(analyzer, "title", hitsFound.Doc(i).Get("title")));
// Console.WriteLine(hitsFound.Doc(i).Get("title"));
}
Console.ReadKey();
}
private static void addDoc(IndexWriter w, String value)
{
Document doc = new Document();
doc.Add(new Field("title", value, Field.Store.YES, Field.Index.ANALYZED));
w.AddDocument(doc);
}
}
The highlighted results always seem to skip the closing '' of my last table tag. Any suggestions?
