c# - 如何使用跨多行的 c# 解析来自文本文件的消息？

Question

给定此日志文件，我如何使用 StreamReader 读取包含多个换行符 (\n) 的行？ReadLine 方法按字面意思返回每一行，但一条消息可能跨越多行。

这是我目前的情况

using (var sr = new StreamReader(filePath))
using (var store = new DocumentStore {ConnectionStringName = "RavenDB"}.Initialize())
{
    IndexCreation.CreateIndexes(typeof(Logs_Search).Assembly, store);

    using (var bulkInsert = store.BulkInsert())
    {
        const char columnDelimeter = '|';
        const string quote = @"~";
        string line;

        while ((line = sr.ReadLine()) != null)
        {
            batch++;
            List<string> columns = null;
            try
            {
                columns = line.Split(columnDelimeter)
                                .Select(item => item.Replace(quote, string.Empty))
                                .ToList();

                if (columns.Count != 5)
                {
                    batch--;
                    Log.Error(string.Join(",", columns.ToArray()));
                    continue;
                }

                bulkInsert.Store(LogParser.Log.FromStringList(columns));

                /* Give some feedback */
                if (batch % 100000 == 0)
                {
                    Log.Debug("batch: {0}", batch);
                }

                /* Use sparingly */
                if (ThrottleEnabled && batch % ThrottleBatchSize == 0)
                {
                    Thread.Sleep(ThrottleThreadWait);
                }
            }
            catch (FormatException)
            {
                if (columns != null) Log.Error(string.Join(",", columns.ToArray()));
            }
            catch (Exception exception)
            {
                Log.Error(exception);
            }
        }
    }                   
}

和模型

public class Log
{
    public string Component { get; set; }
    public string DateTime { get; set; }
    public string Logger { get; set; }
    public string Level { get; set; }
    public string ThreadId { get; set; }
    public string Message { get; set; }
    public string Terms { get; set; }

    public static Log FromStringList(List<string> row)
    {
        Log log = new Log();

        /*log.Component = row[0] == string.Empty ? null : row[0];*/
        log.DateTime = row[0] == string.Empty ? null : row[0].ToLower();
        log.Logger = row[1] == string.Empty ? null : row[1].ToLower();
        log.Level = row[2] == string.Empty ? null : row[2].ToLower();
        log.ThreadId = row[3] == string.Empty ? null : row[3].ToLower();
        log.Message = row[4] == string.Empty ? null : row[4].ToLower();

        return log;
    }
}

Answer 1

我会使用 Regex.Split并在每个错误的开头将文件分解为与日期模式(例如 2013-06-19)匹配的任何内容。