Question

我试图解析具有分配地址和解除分配地址的文本文件

示例文件

02/01/18:09:36:48[INFO]::Allocation (FUNC)Get the values of Items -> Item :233272976
02/01/18:09:36:48[INFO]::Allocation (FUNC)Get the values of Items -> Item :233273480
02/01/18:09:36:48[INFO]::Allocation (FUNC)Get the values of Items -> Item :233273648
02/01/18:09:36:49[INFO]::Allocation (FUNC)Get the values of Items -> Item :233270456
02/01/18:09:36:49[INFO]::Allocation (FUNC)Get the values of Items -> Item :233270120
02/01/18:09:36:49[INFO]::Allocation (FUNC)Get the values of Items -> Item :233273816
02/01/18:09:36:49[INFO]::Allocation (FUNC)Get the values of Items -> Item :233273984
02/01/18:09:36:49[INFO]::Allocation (FUNC)Get the values of Items -> Item :233274152
02/01/18:09:36:49[INFO]::Allocation (FUNC)Get the values of Items -> Item :233269952
02/01/18:09:36:49[INFO]::Allocation (FUNC)Get the values of Items -> Item :233270624
02/01/18:09:36:50[INFO]::Allocation (FUNC)Get the values of Items -> Item :233270288
02/01/18:09:36:50[INFO]::Allocation (FUNC)Get the values of Items -> Item :233274992
02/01/18:09:36:50[INFO]::Allocation (FUNC)Get the values of Items -> Item :195645608
02/01/18:09:36:51[INFO]::Allocation (FUNC)Get the values of Items -> Item :195645944
02/01/18:09:36:51[INFO]::Allocation (FUNC)Get the values of Items -> Item :195646616
02/01/18:09:36:51[INFO]::Allocation (FUNC)Get the values of Items -> Item :195646952
02/01/18:09:36:51[INFO]::Allocation (FUNC)Get the values of Items -> Item :195648128
02/01/18:09:36:54[INFO]::Allocation (FUNC)Get the values of Items -> Item :195638384
02/01/18:09:36:54[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :233272976
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :233270120
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :233273984
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195646112
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195648800
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195647288
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195644096
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195646448
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195644600
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195646784
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195646280
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195648632
02/01/18:09:36:55[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195648128
02/01/18:09:37:00[INFO]::Deallocation (FUNC)Delete the values of Item -> Item :195638384

这是我试图解析的程序

class ReadFromFile1
{

   static Dictionary<int, int> IndexesTobeRemoved;
   static List<string> linesList;
   static string strFileName = @"C:\LogFile.Log";

   static void Main()
   {
             linesList = File.ReadAllLines(strFileName).ToList();

             IndexesTobeRemoved = new Dictionary<int, int>();

             bool bRet = false;
            int iAllocationIndex = 0;
            do
            {
              bRet = RepeatIfMatchFound(ref iAllocationIndex);
            } while (bRet);


         foreach (KeyValuePair<int, int> item in IndexesTobeRemoved)
         {
           linesList[item.Value] = " ";
         }
        File.WriteAllLines(strFileName, linesList.ToArray());
   }

   private static bool RepeatIfMatchFound(ref int iAllocationIndex)
   {
  bool bRet = false;

  for (; iAllocationIndex < linesList.Count - 1; ++iAllocationIndex )
  {
     int iTempIndex = iAllocationIndex;

     if (IndexesTobeRemoved.ContainsValue(iTempIndex)) continue;


     string line = linesList[iAllocationIndex];
     string strAllocationLine = line;
     string strPointerId = string.Empty;
     // Search For Allocation
     if (line.Contains("Allocation"))
     {
        int iIndex = line.IndexOf("Item :");
        strPointerId = line.Substring(iIndex + 6, line.Length - 1 - (iIndex + 5));
        for (int iDeAllocationIndex = iAllocationIndex; iDeAllocationIndex < linesList.Count - 1; ++iDeAllocationIndex)
        {

           if (IndexesTobeRemoved.ContainsValue(iDeAllocationIndex)) continue;

           string strDeallocationLine = linesList[iDeAllocationIndex];

           if (strDeallocationLine.Contains("Deallocation"))
           {
              if (strDeallocationLine.Contains(strPointerId))
              {
                 Console.WriteLine("Found {0} AllocIndex {1} DeAllocIndex {2}", strPointerId, iAllocationIndex+1, iDeAllocationIndex+1);

                 IndexesTobeRemoved.Add(iAllocationIndex, iAllocationIndex);
                 IndexesTobeRemoved.Add(iDeAllocationIndex, iDeAllocationIndex);

                 bRet = true;
                 break;
              }
           }
        }
     }
     if (bRet) break;
  }
  return bRet;
   }
}

关于解析 4 MB 文件，花了6个多小时才继续，我在这里遗漏了什么？

感谢您的帮助。

Answer 1

感谢他LasseVågsætherKarlsen的gist link，重新编写了该程序，速度要快得多。

    public struct stReferenceMatch
{
    public bool bAllocated;
    public bool bDeAllocated;
}


class ReadFromFile1
{
    static string strFileName = @"C:\LogFile.Log";

    static void Main()
    {
        List<string>  linesList = File.ReadAllLines(strFileName).ToList();

        Dictionary<int, stReferenceMatch> IndexesTobeRemoved = new Dictionary<int, stReferenceMatch>();

        foreach (string line in linesList)
        {
            bool bAlloc, bDeAlloc;
            FindAllocDeAllocInString(line, out bAlloc, out bDeAlloc);

            if (bAlloc || bDeAlloc)
            {
                int iIndex = line.IndexOf("Item :");
                string strPointerId = line.Substring(iIndex + 6, line.Length - 1 - (iIndex + 5));
                int iPos = Convert.ToInt32(strPointerId);

                IndexesTobeRemoved.TryGetValue(iPos, out stReferenceMatch refMatch);
                if (bAlloc) refMatch.bAllocated = true;
                if (bDeAlloc) refMatch.bDeAllocated = true;
            }

        }
        using (var writer = new StreamWriter(@"C:\output_new.txt"))
        {
            foreach (var line in linesList)
            {

                bool bAlloc, bDeAlloc;
                FindAllocDeAllocInString(line, out bAlloc, out bDeAlloc);
                if (bAlloc || bDeAlloc)
                {
                    int iIndex = line.IndexOf("Item :");
                    string strPointerId = line.Substring(iIndex + 6, line.Length - 1 - (iIndex + 5));
                    int iPos = Convert.ToInt32(strPointerId);


                    IndexesTobeRemoved.TryGetValue(iPos, out stReferenceMatch refMatch);

                    if (refMatch.bAllocated && refMatch.bDeAllocated)
                        continue;
                }
                else
                {
                    writer.WriteLine(line);
                }

            }
        }


    }

    private static bool FindAllocDeAllocInString(string line, out bool bAlloc, out bool bDeAlloc)
    {
        // Search For Allocation & DeAllocation
        bAlloc = line.Contains("Allocation");
        bDeAlloc = line.Contains("Deallocation");

        return bAlloc || bDeAlloc;
    }
}

解析分配并将其与解除分配相匹配 - 花费大量时间

1 个答案: