A few weeks ago, I wrote a prototype for the meme tracking feature of RSS Bandit in IronPython. The code was included in my blog post A Meme Tracker In IronPython.   The script was a port of Sam Ruby's original MeMeme script which shows the most recently popular links from from a set of RSS feeds.

I was impressed with how succinct the code was in IronPython when compared to what the code eventually looked like when I ported it to C# 2.0 and integrated it into RSS Bandit. Looking over the list of new features in C# 3.0, it occurred to me that a C# 3.0 version of the script would be as concise or even more concise than the IronPython version. So I ported the script to C# 3.0 and learned a few things along the way.

I'll post something shortly that goes into some details on my perspectives on the pros and cons of the various C# 3.0 features when compared to various Python features. For now, here's the meme tracker script in C# 3.0. Comparing it to the IronPython version should provide some food for thought.

using System;
using System.Collections;
using System.Collections.Generic;
using System.Linq;
using System.Text.RegularExpressions;
using System.IO;
using System.Xml;
using System.Xml.Linq;
using System.Xml.XPath;
using System.Globalization;

namespace Memetracker {

    enum MemeMode { PopularInUnread, PopularInPastWeek }

    class RankedLink{
       public string Url { get; set;}
       public double Score { get; set; }   
    }

    class Vote {
        public double Weight { get; set; }
        public RssItem Item { get; set; }
        public string FeedTitle { get; set; }
    }


    class RssItem {
        public string Title { get; set; }
        public DateTime Date { get; set; }
        public bool Read { get; set; }
        public string Permalink { get; set; }
        public Dictionary<string, string> OutgoingLinks { get; set; }
    }

    class Program {

        static Dictionary<string, List<Vote>> all_links = new Dictionary<string, List<Vote>>();
        static TimeSpan one_week = new TimeSpan(7, 0, 0, 0);
        static MemeMode mode = MemeMode.PopularInPastWeek;

        static string cache_location = Path.Combine(Environment.GetFolderPath(Environment.SpecialFolder.LocalApplicationData), "Temp");
        static string href_regex = @"<a[\s]+[^>]*?href[\s]?=[\s""']+(.*?)[\""']+.*?>([^<]+|.*?)?<\/a>";
        static Regex regex       = new Regex(href_regex);

        static RssItem MakeRssItem(XElement itemnode) {

            XElement link_node = itemnode.Element("link");
            var permalink = (link_node == null ? "" : link_node.Value);
            XElement title_node = itemnode.Element("title");
            var title = (title_node == null ? "" : title_node.Value);
            XElement date_node = itemnode.Element("pubDate");
            var date = (date_node == null ? DateTime.Now : DateTime.Parse(date_node.Value, null, DateTimeStyles.AdjustToUniversal));
            XAttribute read_node = itemnode.XPathEvaluate("//@*[local-name() = 'read']") as XAttribute;
            var read = (read_node == null ? false : Boolean.Parse(read_node.Value));
            XElement desc_node = itemnode.Element("description");
            // obtain href value and link text pairs
            var outgoing = (desc_node == null ? regex.Matches(String.Empty) : regex.Matches(desc_node.Value));
            var outgoing_links = new Dictionary<string, string>();
            //ensure we only collect unique href values from entry by replacing list returned by regex with dictionary
            if (outgoing.Count > 0) {
                foreach (Match m in outgoing)
                    outgoing_links[m.Groups[1].Value] = m.Groups[2].Value;
            }
            return new RssItem() { Permalink = permalink, Title = title, Date = date, Read = read, OutgoingLinks = outgoing_links };
        }

        static void Main(string[] args) {

            if (args.Length > 0) //get directory of RSS feeds
                cache_location = args[0];
            if (args.Length > 1) //mode = 0 means use only unread items, mode != 0 means use all items from past week
                mode = (Int32.Parse(args[1]) != 0 ? MemeMode.PopularInPastWeek : MemeMode.PopularInUnread);

            Console.WriteLine("Processing items from {0} seeking items that are {1}", cache_location,
                (mode == MemeMode.PopularInPastWeek ? "popular in items from the past week" : "popular in unread items"));
            
            //decide what filter function to use depending on mode 
            Func<RssItem, bool> filterFunc = null;
            if(mode == MemeMode.PopularInPastWeek) 
                filterFunc = x => (DateTime.Now - x.Date < one_week) ;
            else 
                filterFunc = x => x.Read == false;

            //in mode = 0 each entry linking to an item counts as a vote, in mode != 0 value of vote depends on item age
            Func<RssItem, double> voteFunc   = null; 
            if(mode == MemeMode.PopularInPastWeek) 
                voteFunc = x => 1.0 - (DateTime.Now.Ticks - x.Date.Ticks) * 1.0 / one_week.Ticks; 
            else 
                voteFunc = x => 1.0;

            
            var di = new DirectoryInfo(cache_location); 
            foreach(var fi in di.GetFiles("*.xml")){
                var doc = XElement.Load(Path.Combine(cache_location, fi.Name));
                // for each item in feed
                //  1. Get permalink, title, read status and date
                //  2. Get list of outgoing links + link title pairs
                //  3. Convert above to RssItem object
                //  4. apply filter to pick candidate items
                var items = from rssitem in 
                            (from itemnode in doc.Descendants("item")                            
                            select MakeRssItem(itemnode))
                            where filterFunc(rssitem)
                            select rssitem;
                var feedTitle = doc.XPathSelectElement("channel/title").Value;
                // calculate vote for each outgoing url
                foreach (RssItem item in items) { 
                    var vote = new Vote(){ Weight=voteFunc(item), Item=item, FeedTitle=feedTitle };
                    //add a vote for each of the URLs
                    foreach (var url in item.OutgoingLinks.Keys) {
                        List<Vote> value = null;
                        if (!all_links.TryGetValue(url, out value))
                            value = all_links[url] = new List<Vote>(); 
                            
                        value.Add(vote);                                                    
                    }
                }// foreach (RssItem item in items)
            }// foreach(var fi in di.GetFiles("*.xml"))
           
            //tally the votes
            List<RankedLink> weighted_links = new List<RankedLink>();
            foreach (var link_n_votes in all_links) {
                Dictionary<string, double> site = new Dictionary<string, double>();
                foreach (var vote in link_n_votes.Value) {
                    double oldweight;
                    site[vote.FeedTitle] = site.TryGetValue(vote.FeedTitle, out oldweight) ? 
                                            Math.Min(oldweight, vote.Weight): vote.Weight; 
                }
                weighted_links.Add(new RankedLink(){Score=site.Values.Sum(), Url=link_n_votes.Key});
            }
            weighted_links.Sort((x, y) => y.Score.CompareTo(x.Score));

            //output the results, choose link text from first item we saw story linked from
            Console.WriteLine("<html><body><ol>");
            foreach(var rankedlink in weighted_links.GetRange(0, 10)){
                var link_text = (all_links[rankedlink.Url][0]).Item.OutgoingLinks[rankedlink.Url];
                Console.WriteLine("<li><a href='{0}'>{1}</a> {2}", rankedlink.Url, link_text, rankedlink.Score);
                Console.WriteLine("<p>Seen on:");
                Console.WriteLine("<ul>");
                foreach (var vote in all_links[rankedlink.Url]) {
                    Console.WriteLine("<li>{0}: <a href='{1}'>{2}</a></li>", vote.FeedTitle, vote.Item.Permalink, vote.Item.Title);
                }
                Console.WriteLine("</ul></p></li>");
            }
            Console.WriteLine("</ol></body></html>");
            Console.ReadLine();
        }
    }
}