Hello: I am using Umbraco 7.5.9 and I have 3 indexers defined and working fine, except when my user search the Umbraco site, it is taking 18 seconds to returns through the three indexers before returning the results. So I retooled the code and utilized C# parallel threading and now my search is done in half the time 9 seconds (still too slow).

For my site, when my users search on "housing" there are a total of 303 items. 131 items belong to the Content indexer. 250 items belong to the pdf indexer, 2 items below to the Inbox indexer (a custom backoffice App PlugIn we wrote.

Question: I have broken my code down and found the bottleneck is in the PDF indexer.

Does anyone have any suggestions on how to improve PDF indexer>

Thank You

Tom

PS Here is the code. Note: I am using ConcurrentBag and Parallel processing.

        var indexesToSearch = new List<Tuple<SearchIndexType, string>>
        {
            new Tuple<SearchIndexType, string>(SearchIndexType.Content, @"MembersOnlyIndexSet"),
            new Tuple<SearchIndexType, string>(SearchIndexType.Media, @"MembersOnlyPDFIndexSet"),
            new Tuple<SearchIndexType, string>(SearchIndexType.InboxMessage, "MembersOnlyInboxMessageIndexSet")
        };


        var results = new List<SearchResultVM>();

        if (string.IsNullOrWhiteSpace(searchTerm))
            return results;

        var analyzer = new StandardAnalyzer(Version.LUCENE_29);
        var parser = new MultiFieldQueryParser(Version.LUCENE_29,
            QueryFields,
            new StandardAnalyzer(Version.LUCENE_29));
        var query = parser.Parse(searchTerm);

        // Build the highlighter
        var formatter = new SimpleHTMLFormatter("<span class=\"lucene-highlight\">", "</span>");
        var scorer = new QueryScorer(query);
        var highlighter = new Highlighter(formatter, scorer);
        highlighter.SetTextFragmenter(new SimpleFragmenter(FragementLength));

        var sets = IndexSets.Instance.Sets;
        UmbracoContext context = UmbracoContext.Current;

        ConcurrentBag<SearchResultVM> bag = new ConcurrentBag<SearchResultVM>();

        Parallel.ForEach(indexSets, (index) =>
        {
            var set = sets[index.Item2];
            var dirInfo = new DirectoryInfo(Path.Combine(set.IndexDirectory.FullName, @"Index"));

            using (var indexDir = FSDirectory.Open(dirInfo))
            {
                using (var indexSearcher = new IndexSearcher(indexDir, true))
                {
                    var collect = TopScoreDocCollector.create(3000, true);
                    indexSearcher.Search(query, collect);

                    var docs = collect.TopDocs();
                    for (int i = 0; i < collect.GetTotalHits(); i++)
                    {
                        var rec = docs.ScoreDocs[i];
                        var doc = indexSearcher.Doc(rec.doc);

                        SearchResultVM item;
                        switch (index.Item1)
                        {
                            case SearchIndexType.Content:
                                item = BuildSearchContentItem(rec, analyzer, highlighter, doc);
                                break;
                            case SearchIndexType.Media:
                                item = BuildSearchMediaItem(rec, analyzer, highlighter, doc, context);
                                break;
                            case SearchIndexType.InboxMessage:
                                item = BuildSearchInboxMessageItem(rec, analyzer, highlighter, doc);
                                break;
                            default:
                                Log.DebugFormat("Unrecognized search index type {0}", index.Item1);
                                item = null;
                                break;
                        }

                        if (item != null)
                        {
                            bag.Add(item);
                        }
                    }
                }
            }
        });

        results = bag.ToList();
        return results.OrderByDescending(o => o.Score).ToList();
    }