public static Lucene.Net.Search.Hits search(Lucene.Net.Search.Query query)
{
Lucene.Net.Search.Hits hits = null;
lock (my_lock) // prevent contention between searches and writing?
{
if (searcher == null)
{
searcher = new Lucene.Net.Search.IndexSearcher(MyLucene.index_path);
}
hits = searcher.Search(query);
}
return(hits);
}
private void QueryTest(Query query)
{
ScoreDoc[] parallelHits = parallel.Search(query, null, 1000).scoreDocs;
ScoreDoc[] singleHits = single.Search(query, null, 1000).scoreDocs;
Assert.AreEqual(parallelHits.Length, singleHits.Length);
for (int i = 0; i < parallelHits.Length; i++)
{
Assert.AreEqual(parallelHits[i].score, singleHits[i].score, 0.001f);
Document docParallel = parallel.Doc(parallelHits[i].doc);
Document docSingle = single.Doc(singleHits[i].doc);
Assert.AreEqual(docParallel.Get("f1"), docSingle.Get("f1"));
Assert.AreEqual(docParallel.Get("f2"), docSingle.Get("f2"));
Assert.AreEqual(docParallel.Get("f3"), docSingle.Get("f3"));
Assert.AreEqual(docParallel.Get("f4"), docSingle.Get("f4"));
}
}
public static void searchFor(Searcher searcher, string querystr)
{
QueryParser parser = new QueryParser("body", new StandardAnalyzer()); // could be outside this function
Query query = parser.Parse(querystr);
var hits = new AnonymousClassCollector();
// more accurate timer
var timer = new Stopwatch();
timer.Start();
searcher.Search(query, hits);
timer.Stop();
Console.WriteLine("search for [{0}] returned {1} hits in {2}ms )",
query, hits.Count, timer.ElapsedMilliseconds);
}
// LUCENE-1404
private int HitCount(Searcher searcher, System.String word)
{
return searcher.Search(new TermQuery(new Term("text", word)), 10).totalHits;
}
// LUCENE-1404
private int HitCount(Searcher searcher, System.String word)
{
return(searcher.Search(new TermQuery(new Term("text", word)), 10).TotalHits);
}
public virtual void DoSearching(Query unReWrittenQuery)
{
searcher = new IndexSearcher(ramDir);
//for any multi-term queries to work (prefix, wildcard, range,fuzzy etc) you must use a rewritten query!
query = unReWrittenQuery.Rewrite(reader);
System.Console.Out.WriteLine("Searching for: " + query.ToString(FIELD_NAME));
hits = searcher.Search(query);
}
public virtual void TestUnRewrittenQuery()
{
//test to show how rewritten query can still be used
searcher = new IndexSearcher(ramDir);
Analyzer analyzer = new StandardAnalyzer();
QueryParser parser = new QueryParser(FIELD_NAME, analyzer);
Query query = parser.Parse("JF? or Kenned*");
System.Console.Out.WriteLine("Searching with primitive query");
//forget to set this and...
//query=query.rewrite(reader);
Hits hits = searcher.Search(query);
//create an instance of the highlighter with the tags used to surround highlighted text
// QueryHighlightExtractor highlighter = new QueryHighlightExtractor(this, query, new StandardAnalyzer());
Highlighter highlighter = new Highlighter(this, new QueryScorer(query));
highlighter.SetTextFragmenter(new SimpleFragmenter(40));
int maxNumFragmentsRequired = 3;
for (int i = 0; i < hits.Length(); i++)
{
System.String text = hits.Doc(i).Get(FIELD_NAME);
TokenStream tokenStream = analyzer.TokenStream(FIELD_NAME, new System.IO.StringReader(text));
System.String highlightedText = highlighter.GetBestFragments(tokenStream, text, maxNumFragmentsRequired, "...");
System.Console.Out.WriteLine(highlightedText);
}
//We expect to have zero highlights if the query is multi-terms and is not rewritten!
Assert.IsTrue(numHighlights == 0, "Failed to find correct number of highlights " + numHighlights + " found");
}
/// <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);
}
}
}
/// <summary> This method uses a custom HitCollector implementation which simply prints out
/// the docId and score of every matching document.
///
/// This simulates the streaming search use case, where all hits are supposed to
/// be processed, regardless of their relevance.
/// </summary>
public static void DoStreamingSearch(Searcher searcher, Query query)
{
Collector streamingHitCollector = new AnonymousClassCollector();
searcher.Search(query, streamingHitCollector);
}
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);
}
/// <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);
}
}
}
/// <summary> This method uses a custom HitCollector implementation which simply prints out
/// the docId and score of every matching document.
///
/// This simulates the streaming search use case, where all hits are supposed to
/// be processed, regardless of their relevance.
/// </summary>
public static void DoStreamingSearch(Searcher searcher, Query query)
{
Collector streamingHitCollector = new AnonymousClassCollector();
searcher.Search(query, streamingHitCollector);
}
