Simple rating algorithm to sorting results accordi

问题:

I'm developing a very basic web search engine that has several parts. After retrieving results according to a user query, I want to calculate rate of each result and then sort results by calculated rate. Here is my query:

var tmpQuery = (from urls in _context.Urls
                join documents in _context.Documents
                  on urls.UrlId equals documents.DocumentId
                let words = (from words in _context.Words
                             join hits in _context.Hits
                               on words.WordId equals hits.WordId
                             where hits.DocumentId == documents.DocumentId
                             select words.Text)
                select new { urls, documents, words });

var results = (from r in tmpQuery.AsEnumerable()
               where r.urls.ResolvedPath.Contains(breakedQuery, KeywordParts.Url, part) ||
                     r.documents.Title.Contains(breakedQuery, KeywordParts.Title, part) ||
                     r.documents.Keywords.Contains(breakedQuery, KeywordParts.Keywords, part) ||
                     r.documents.Description.Contains(breakedQuery, Description, part) ||
                     r.words.Contains(breakedQuery, KeywordParts.Content, part)

                     select new SearchResult()
                     {
                        UrlId = r.urls.UrlId,
                        Url = r.urls.ResolvedPath,
                        IndexedOn = r.documents.IndexedOn,
                        Title = r.documents.Title,
                        Description = r.documents.Description,
                        Host = new Uri(r.urls.ResolvedPath).Host,
                        Length = r.documents.Length,
                        Rate = 0CalculateRating(breakedQuery, r.urls.ResolvedPath, r.documents.Title, r.documents.Keywords, r.documents.Description, r.words)
                     }).AsEnumerable()
                     .OrderByDescending(result => result.Rate)
                     .Distinct(new SearchResultEqualityComparer());

and rate is calculated by this method:

private int CalculateRating(IEnumerable<string> breakedQuery, string resolvedPath, string title, string keywords, string description, IEnumerable<string> words)
    {
        var baseRate = 0;

        foreach (var query in breakedQuery)
        {
            /*first I'm breaking up user raw query (Microsoft -Apple) to list of broken
            queries (Microsoft, -Apple) if broken query start with - that means
            results shouldn't have*/
            var none = (query.StartsWith("-"));
            string term = query.Replace("-", "");

            var pathCount = Calculate(resolvedPath, term);
            var titleCount = Calculate(title, term);
            var keywordsCount = Calculate(keywords, term);
            var descriptionCount = Calculate(description, term);
            var wordsCount = Calculate(words, term);

            var result = (pathCount * 100) + (titleCount * 50) + (keywordsCount * 25) + (descriptionCount * 10) + (wordsCount);

            if (none)
                baseRate -= result;
            else
                baseRate += result;
        }
        return baseRate;
    }

    private int Calculate(string source, string query)
    {
        if (!string.IsNullOrWhiteSpace(source))
            return Calculate(source.Split(' ').AsEnumerable<string>(), query);
        return 0;
    }

    private int Calculate(IEnumerable<string> sources, string query)
    {
        var count = 0;
        if (sources != null && sources.Count() > 0)
        {
            //to comparing two strings
            //first case sensitive
            var elements = sources.Where(source => source == query);
            count += elements.Count();
            //second case insensitive (half point of sensitive)
            count += sources.Except(elements).Where(source => source.ToLowerInvariant() == query.ToLowerInvariant()).Count() / 2;
        }
        return count;
    }

Please guide me to improve performance (speed of my search engine is very very low)

回答1:

I expect this is down to your from urls in _context.Urls - with no Where on this you're getting a lot of data to then throw away when building up your results. How many items are in tmpQuery / results?