Question

我有两个字典，我试图加入并将匹配的索引保存在单独的字典中，如下所示：

public class MatchedPairs
    {
        public List<int> index1;
        public List<int> index2;

        public MatchedPairs()
        {
            this.index1 = new List<int>();
            this.index2 = new List<int>();
        }
    }

Dictionary<int, string> file1Dictionary = new Dictionary<int, string>();
Dictionary<int, string> file2Dictionary = new Dictionary<int, string>();

//Fill dictionaries with data from flat files
//...

var matchedKeys = file1Dictionary.Join(file2Dictionary, x => x.Value, y => y.Value, (x, y) => new { k1 = x.Key, k2 = y.Key });

Dictionary<int, MatchedPairs> matches = new Dictionary<int, MatchedPairs>(); 

foreach (var match in matchedKeys)
{
    matches.index1.Add(match.k1);
    matches.index2.Add(match.k2);
}

我收到了

内存不足异常

执行此代码时，因为file1Dictionary和file2Dictionary个对象中有数百万个条目。

我能做些什么来在内存/ C＃中匹配这些大对象。我的另一种方法是将数据加载到SQL数据库中并在那里进行加入。感谢。

Answer 1

我认为你的词典应该是Dictionary＆lt; string，MatchedPairs＆gt;匹配（不是整数）。

    class Program
    {
        static void Main(string[] args)
        {

           Dictionary<int, string> file1Dictionary = new Dictionary<int, string>();
           Dictionary<int, string> file2Dictionary = new Dictionary<int, string>();

           //Fill dictionaries with data from flat files
           //...
           Dictionary<string, List<int>> reverseDict1 = file1Dictionary.Keys.AsEnumerable()
               .Select(x => new { value = x, keys = file1Dictionary[x] })
               .GroupBy(x => x.keys, y => y.value)
               .ToDictionary(x => x.Key, y => y.ToList());

           Dictionary<string, List<int>> reverseDict2 = file1Dictionary.Keys.AsEnumerable()
               .Select(x => new { value = x, keys = file2Dictionary[x] })
               .GroupBy(x => x.keys, y => y.value)
               .ToDictionary(x => x.Key, y => y.ToList());

           Dictionary<string, MatchedPairs> matches = new Dictionary<string, MatchedPairs>();
           foreach(string key in reverseDict1.Keys)
           {
               matches.Add(key, new MatchedPairs(reverseDict1[key], reverseDict2[key]));
           }

        }
    }
    public class MatchedPairs
    {
        public List<int> index1 { get; set; }
        public List<int> index2 { get; set; }

        public MatchedPairs(List<int> l1, List<int> l2)
        {
            this.index1 = new List<int>(l1);
            this.index2 = new List<int>(l2);
        }
    }

LINQ加入非常大的字典/内存不足异常

1 个答案: