C#大文件读取和查询--内存映射

笔者最近需要快速查询日志文件,文件大小在4G以上。

需求如下:

1.读取4G左右大小的文件中的指定行，程序运行占用内存不超过500M。

2.希望查询1G以内容,能控制在20s左右.

刚开始觉得这个应该不难.研究一天之后,发现这个需要使用内存映射技术。

查阅了相关资料之后

https://msdn.microsoft.com/zh-cn/library/dd997372(v=vs.110).aspx?cs-save-lang=1&cs-lang=csharp#code-snippet-1

发现还是有一定的复杂性.特别是需要对字符处理。

笔者自己写了一个Demo,希望实现

很遗憾,测试结果,查询1G左右的内容,花费时间在100s左右.

程序如下:

using System;
using System.IO;
using System.IO.MemoryMappedFiles;
using System.Text;

namespace ConsoleDemo
{
    class Program
    {
        private const string TXT_FILE_PATH = @"E:\开源学习\超大文本文件读取\File\a.txt";
        private const string SPLIT_VARCHAR = "囧";
        private const char SPLIT_CHAR = '囧';
        private static long FILE_SIZE = 0;
        static void Main(string[] args)
        {
            //long ttargetRowNum = 39999999;
            long ttargetRowNum = 10000000;
            DateTime beginTime = DateTime.Now;
            string line = CreateMemoryMapFile(ttargetRowNum);
            double totalSeconds = DateTime.Now.Subtract(beginTime).TotalSeconds;
            Console.WriteLine(line);
            Console.WriteLine(string.Format("查找第{0}行,共耗时:{1}s", ttargetRowNum, totalSeconds));
            Console.ReadLine();
        }

        /// <summary>
        /// 创建内存映射文件
        /// </summary>
        private static string CreateMemoryMapFile(long ttargetRowNum)
        {
            string line = string.Empty;
            using (FileStream fs = new FileStream(TXT_FILE_PATH, FileMode.Open, FileAccess.ReadWrite))
            {
                long targetRowNum = ttargetRowNum + 1;//目标行
                long curRowNum = 1;//当前行
                FILE_SIZE = fs.Length;
                using (MemoryMappedFile mmf = MemoryMappedFile.CreateFromFile(fs, "test", fs.Length, MemoryMappedFileAccess.ReadWrite, null, HandleInheritability.None, false))
                {
                    long offset = 0;
                    //int limit = 250;
                    int limit = 200;
                    try
                    {
                        StringBuilder sbDefineRowLine = new StringBuilder();
                        do
                        {
                            long remaining = fs.Length - offset;
                            using (MemoryMappedViewStream mmStream = mmf.CreateViewStream(offset, remaining > limit ? limit : remaining))
                            //using (MemoryMappedViewStream mmStream = mmf.CreateViewStream(offset, remaining))
                            {
                                offset += limit;
                                using (StreamReader sr = new StreamReader(mmStream))
                                {
                                    //string ss = sr.ReadToEnd().ToString().Replace("\n", "囧").Replace(Environment.NewLine, "囧");
                                    string ss = sr.ReadToEnd().ToString().Replace("\n", SPLIT_VARCHAR).Replace(Environment.NewLine, SPLIT_VARCHAR);
                                    if (curRowNum <= targetRowNum)
                                    {
                                        if (curRowNum < targetRowNum)
                                        {
                                            string s = sbDefineRowLine.ToString();
                                            int pos = s.LastIndexOf(SPLIT_CHAR);
                                            if (pos > 0)
                                                sbDefineRowLine.Remove(0, pos);

                                        }
                                        else
                                        {
                                            line = sbDefineRowLine.ToString();
                                            return line;
                                        }
                                        if (ss.Contains(SPLIT_VARCHAR))
                                        {
                                            curRowNum += GetNewLineNumsOfStr(ss);
                                            sbDefineRowLine.Append(ss);
                                        }
                                        else
                                        {
                                            sbDefineRowLine.Append(ss);
                                        }
                                    }
                                    //sbDefineRowLine.Append(ss);
                                    //line = sbDefineRowLine.ToString();
                                    //if (ss.Contains(Environment.NewLine))
                                    //{
                                    //    ++curRowNum;
                                    //    //curRowNum++;
                                    //    //curRowNum += GetNewLineNumsOfStr(ss);
                                    //    //sbDefineRowLine.Append(ss);
                                    //}
                                    //if (curRowNum == targetRowNum)
                                    //{
                                    //    string s = "";
                                    //}

                                    sr.Dispose();
                                }

                                mmStream.Dispose();
                            }
                        } while (offset < fs.Length);
                    }
                    catch (Exception e)
                    {
                        Console.WriteLine(e.Message);
                    }
                    return line;
                }
            }
        }

        private static long GetNewLineNumsOfStr(string s)
        {
            string[] _lst = s.Split(SPLIT_CHAR);
            return _lst.Length - 1;
        }
    }
}

测试截图:

 

欢迎大家提供更好的解决思路.

参考资料:

https://msdn.microsoft.com/zh-cn/library/dd997372(v=vs.110).aspx?cs-save-lang=1&cs-lang=csharp#code-snippet-1

http://blog.csdn.net/onejune2013/article/details/7577152