Question

I got an XML file that is 9MB large. Apparently, it is broken.

I want to check if on any level 2 sibling elements have an attribute “Id” with same value.

Currently it goes too slow. What kind of optimizations I could make to this code?

Edited to include some tips

namespace ConsoleApplication1{
  using System;
  using System.Collections.Generic;
  using System.Diagnostics;
  using System.IO;
  using System.Linq;
  using System.Xml.Linq;
  internal class Program{
    private const string _pathToXml=@"C:\4\4";
    private static readonly List<object> _duplicateLeafs=new List<object>();
    private static void Main(){
      var xml=ReadXml();
      var elements=xml.Descendants();
      foreach(var element in elements)
        FindDupes(element);
      Console.ReadLine();
      Debugger.Break();
    }
    private static XDocument ReadXml(){
      return XDocument.Parse(File.ReadAllText(_pathToXml));
    }
    private static void FindDupes(XElement element){
      var elements=element.Descendants();
      var elementsWithIds=elements.Where(x=>x.Attribute("Id")!=null);
      var ids=elementsWithIds.Select(x=>x.Attribute("Id")).ToList();
      for(var i=0;i<ids.Count;i++)
        for(var j=i+1;j<ids.Count;j++)
          if(i!=j&&ids[i]==ids[j])
            _duplicateLeafs.Add(elementsWithIds.First(x=>x.Attribute("Id")==ids[i]));
      foreach(var subElement in elements)
        FindDupes(subElement);
    }
  }
}

Answer 1

You say you want to check level 2 descendants, but yet FindDupes is recursive, so you’re recursively checking two levels deep in foreach loops, every call.