public Task <IEnumerable <ISearchItem> > Search(string pattern, int page)
{
using (Analyzer analyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48))
using (Lucene.Net.Store.Directory index = new SimpleFSDirectory(Path.ChangeExtension(_bookFile.FullName,
Convert.ToInt32(LuceneVersion.LUCENE_48).ToString())))
using (IndexReader reader = DirectoryReader.Open(index))
{
Lucene.Net.Search.Query query =
new QueryParser(LuceneVersion.LUCENE_48, nameof(TabHtmlText.Html), analyzer).Parse(pattern);
Lucene.Net.Search.TopScoreDocCollector collector =
Lucene.Net.Search.TopScoreDocCollector.Create(512, true);
Lucene.Net.Search.IndexSearcher searcher = new Lucene.Net.Search.IndexSearcher(reader);
searcher.Search(query, collector);
Lucene.Net.Search.TopDocs docs = collector.GetTopDocs(page * PageSize, PageSize);
QueryScorer scorer = new QueryScorer(query);
Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(), scorer) // SpanGradientFormatter
{
TextFragmenter = new SimpleSpanFragmenter(scorer, 30)
};
IEnumerable <ISearchItem> items = docs.ScoreDocs.Select(scoreDoc =>
{
Document doc = searcher.Doc(scoreDoc.Doc);
string html = doc.Get(nameof(TabHtmlText.Html));
string[] fragments = highlighter.GetBestFragments(new HTMLStripCharAnalyzer(),
nameof(TabHtmlText.Html), html, 3);
return(new SearchItem(int.Parse(doc.Get(nameof(TabHtmlText.NumId))), string.Join("\n", fragments)));
});
return(Task.FromResult(items.ToList().AsEnumerable()));
}
}
public List <indexVideo> searchArticles(string queryString, int numberOfResults, bool komin)
{
List <indexVideo> resultsList = new List <indexVideo>();
Lucene.Net.Store.Directory index = publicIndex;
if (komin)
{
index = kominIndex;
}
if (!string.IsNullOrEmpty(queryString))
{
Lucene.Net.QueryParsers.QueryParser parser = new Lucene.Net.QueryParsers.MultiFieldQueryParser(Lucene.Net.Util.Version.LUCENE_30, new[] { "title", "shortDescription" }, analyser);
try
{
Lucene.Net.Search.Query query = parser.Parse(queryString + "~");
Lucene.Net.Search.Searcher searcher = new Lucene.Net.Search.IndexSearcher(index, true);
Lucene.Net.Search.TopScoreDocCollector collector = Lucene.Net.Search.TopScoreDocCollector.Create(numberOfResults, true);
searcher.Search(query, collector);
Lucene.Net.Search.ScoreDoc[] hits = collector.TopDocs().ScoreDocs;
if (hits.Length >= 1)
{
for (int i = 0; i < hits.Length; i++)
{
indexVideo video = new indexVideo();
int docId = hits[i].Doc;
float score = hits[i].Score;
Lucene.Net.Documents.Document doc = searcher.Doc(docId);
video.bctid = doc.Get("bctid");
video.title = doc.Get("title");
video.score = score;
video.shortDescription = doc.Get("shortDescription");
video.imageURL = doc.Get("imageURL");
resultsList.Add(video);
}
}
}
catch (Exception e)
{
}
}
return(resultsList);
}
private bool videoExistsInIndex(string id, Lucene.Net.Store.Directory index)
{
bool exist = false;
Lucene.Net.Search.TermQuery termQuery = new Lucene.Net.Search.TermQuery(new Lucene.Net.Index.Term("bctid", id));
Lucene.Net.Search.Searcher termSearcher = new Lucene.Net.Search.IndexSearcher(index, true);
Lucene.Net.Search.TopScoreDocCollector termCollector = Lucene.Net.Search.TopScoreDocCollector.Create(1, true);
termSearcher.Search(termQuery, termCollector);
int termResults = termCollector.TopDocs().TotalHits;
if (termResults > 0)
{
exist = true;
}
return(exist);
}
/// <summary> This demonstrates a typical paging search scenario, where the search engine presents
/// pages of size n to the user. The user can then go to the next page if interested in
/// the next hits.
///
/// When the query is executed for the first time, then only enough results are collected
/// to fill 5 result pages. If the user wants to page beyond this limit, then the query
/// is executed another time and all hits are collected.
///
/// </summary>
public static void DoPagingSearch(System.IO.StreamReader in_Renamed, Searcher searcher, Query query, int hitsPerPage, bool raw, bool interactive)
{
// Collect enough docs to show 5 pages
TopScoreDocCollector collector = TopScoreDocCollector.create(5 * hitsPerPage, false);
searcher.Search(query, collector);
ScoreDoc[] hits = collector.TopDocs().scoreDocs;
int numTotalHits = collector.GetTotalHits();
System.Console.Out.WriteLine(numTotalHits + " total matching documents");
int start = 0;
int end = System.Math.Min(numTotalHits, hitsPerPage);
while (true)
{
if (end > hits.Length)
{
System.Console.Out.WriteLine("Only results 1 - " + hits.Length + " of " + numTotalHits + " total matching documents collected.");
System.Console.Out.WriteLine("Collect more (y/n) ?");
System.String line = in_Renamed.ReadLine();
if (line.Length == 0 || line[0] == 'n')
{
break;
}
collector = TopScoreDocCollector.create(numTotalHits, false);
searcher.Search(query, collector);
hits = collector.TopDocs().scoreDocs;
}
end = System.Math.Min(hits.Length, start + hitsPerPage);
for (int i = start; i < end; i++)
{
if (raw)
{
// output raw format
System.Console.Out.WriteLine("doc=" + hits[i].doc + " score=" + hits[i].score);
continue;
}
Document doc = searcher.Doc(hits[i].doc);
System.String path = doc.Get("path");
if (path != null)
{
System.Console.Out.WriteLine((i + 1) + ". " + path);
System.String title = doc.Get("title");
if (title != null)
{
System.Console.Out.WriteLine(" Title: " + doc.Get("title"));
}
}
else
{
System.Console.Out.WriteLine((i + 1) + ". " + "No path for this document");
}
}
if (!interactive)
{
break;
}
if (numTotalHits >= end)
{
bool quit = false;
while (true)
{
System.Console.Out.Write("Press ");
if (start - hitsPerPage >= 0)
{
System.Console.Out.Write("(p)revious page, ");
}
if (start + hitsPerPage < numTotalHits)
{
System.Console.Out.Write("(n)ext page, ");
}
System.Console.Out.WriteLine("(q)uit or enter number to jump to a page.");
System.String line = in_Renamed.ReadLine();
if (line.Length == 0 || line[0] == 'q')
{
quit = true;
break;
}
if (line[0] == 'p')
{
start = System.Math.Max(0, start - hitsPerPage);
break;
}
else if (line[0] == 'n')
{
if (start + hitsPerPage < numTotalHits)
{
start += hitsPerPage;
}
break;
}
else
{
int page = System.Int32.Parse(line);
if ((page - 1) * hitsPerPage < numTotalHits)
{
start = (page - 1) * hitsPerPage;
break;
}
else
{
System.Console.Out.WriteLine("No such page");
}
}
}
if (quit)
{
break;
}
end = System.Math.Min(numTotalHits, start + hitsPerPage);
}
}
}
