c# - 解析日志文件，不明确的分隔符

Question

我必须解析一个日志文件，但不确定如何最好地获取每行的不同部分。我面临的问题是原始开发人员使用'：'来分隔令牌，这有点愚蠢，因为该行包含本身包含'：'的时间戳！

示例行如下所示：

transaction_date_time:[systemid]:sending_system:receiving_system:data_length:data:[ws_name]

2019-05-08 15:03:13:494|2019-05-08 15:03:13:398:[192.168.1.2]:ABC:DEF:67:cd71f7d9a546ec2b32b,AACN90012001000012,OPNG:[WebService.SomeName.WebServiceModule::WebServiceName]

我读取日志文件并访问每一行没有问题，但不知道如何解析这些片段？

标签： c#parsing

Answer 1

使用正则表达式我能够解析所有内容。看起来数据来自excel，因为秒的派系有一个冒号而不是句号。c# 不喜欢冒号，所以我不得不用句号替换冒号。我还从右到左解析以解决冒号问题。

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Text.RegularExpressions;
using System.IO;


namespace ConsoleApplication3
{
    class Program1
    {
        const string FILENAME = @"c:\temp\test.txt";
        static void Main(string[] args)
        {
            string line = "";
            int rowCount = 0;
            StreamReader reader = new StreamReader(FILENAME);
            string pattern = @"^(?'time'.*):\[(?'systemid'[^\]]+)\]:(?'sending'[^:]+):(?'receiving'[^:]+):(?'length'[^:]+):(?'data'[^:]+):\[(?'ws_name'[^\]]+)\]";

            while ((line = reader.ReadLine()) != null)
            {
                line = line.Trim();
                if (line.Length > 0)
                {
                    if (++rowCount != 1) //skip header row
                    {
                        Log_Data newRow = new Log_Data();
                        Log_Data.logData.Add(newRow);
                        Match match = Regex.Match(line, pattern, RegexOptions.RightToLeft);

                        newRow.ws_name = match.Groups["ws_name"].Value;
                        newRow.data = match.Groups["data"].Value;
                        newRow.length = int.Parse(match.Groups["length"].Value);
                        newRow.receiving_system = match.Groups["receiving"].Value;
                        newRow.sending_system = match.Groups["sending"].Value;
                        newRow.systemid  = match.Groups["systemid"].Value;
                        //end data is first then start date is second
                        string[] date = match.Groups["time"].Value.Split(new char[] {'|'}).ToArray();
                        string replacePattern = @"(?'leader'.+):(?'trailer'\d+)";
                        string stringDate = Regex.Replace(date[1], replacePattern, "${leader}.${trailer}", RegexOptions.RightToLeft);
                        newRow.startDate = DateTime.Parse(stringDate);
                        stringDate = Regex.Replace(date[0], replacePattern, "${leader}.${trailer}", RegexOptions.RightToLeft);
                        newRow.endDate = DateTime.Parse(stringDate );
                    }
                }
            }


        }
    }
    public class Log_Data
    {
        public static List<Log_Data> logData = new List<Log_Data>();

        public DateTime startDate { get; set; } //transaction_date_time:[systemid]:sending_system:receiving_system:data_length:data:[ws_name]
        public DateTime endDate { get; set; }
        public string systemid { get; set; }
        public string sending_system { get; set; }
        public string receiving_system { get; set; }
        public int length { get; set; }
        public string data { get; set; }
        public string ws_name { get; set; }
    }
}