Question

我有一个日志文本文件，我想对其进行总结。下面是我的日志文本文件示例。

Date        |ID    |Folder               |Doc   |FileName   |NoOfAcct| 
20181024    |1     |ABC.20181101.CGLOG   |test  |xxxx       |12
20181024    |2     |CDE.20181013.CGLOG   |home  |XyyX       |2
20181024    |3     |WQE.20181013.CGLOG   |office|xy         |5
20181024    |4     |ABC.20181013.CGLOG   |store |yy         |10

我想对其进行总结，并用Folder和ID将它分开（ group ）。例如，我要将具有Folder号 1 的ID ABC.20181101.CGLOG 复制到新文本文件 。我确实编写了一些代码，但是我被卡住了。

using System;
using System.IO;

namespace HLB
{
    internal class Program
    {
        private static void Main(string[] args)
        {
            string path1 = "";                
            if (path1 == "")
                path1 = "F:\\Work\\FLP Code\\test\\log_test.txt";            
            string[] strArray1 = File.ReadAllLines(path1);
            string fileName = Path.GetFileName(path1);
            string directoryName = Path.GetDirectoryName(path1);
            if (fileName.Contains("%ABC%"))
            {
                Console.WriteLine("Test!");
            }
        }
    }
}

有人可以帮我给我一个例子吗？预先感谢。

大家好，下面是我的新代码：

using System;
using System.IO;
using System.Linq;

namespace HLB
{
    internal class Program
    {
        private static void Main(string[] args)
        {
            // Our initial data
            string path1 = "";
            if (path1 == "")
                path1 = "F:\\Work\\FLP Code\\test\\log_test.txt";
            var data = File
            .ReadLines(path1)
            .Skip(1) // Skip 1st record (header)
            .Where(line => !string.IsNullOrWhiteSpace(line)) // remove empty lines, if any 
            .Select(line => line.Split('|'))                 // split each line by |
            .Select(items => new {
                Raw = string.Join("|", items),               // Raw data as it is in the file

                Date = items[0].Trim(),
                ID = items[1].Trim(),
                Folder = items[2].Trim(),
                Doc = items[3].Trim(),
                FileName = items[4].Trim(),
                NoOfAct = items[5].Trim(),
            });

                // Now, it's quite easy to represent the data as we want.
                // And we want to *group by* `Folder` and `ID`: just one GroupBy operation
                var result = data
                    .GroupBy(item => new {
                        ID = item.ID,
                        Folder = item.Folder
                    })
                    .Select(chunk =>
                    $"File {chunk.Key.Folder + "_" + chunk.Key.ID}.txt :\r\n  {string.Join(Environment.NewLine + "  ", chunk.Select(item => item.Raw))}");

                foreach (var record in result)
                    Console.WriteLine(record);

            File.WriteAllLines(@"F:\\Work\\FLP Code\\test\\MyNewTextFile.txt", data
            .Where(item => item.ID == "1" &&
            item.Folder == "ABC.20181101.CGLOG")
            .Select(item => item.Raw));
        }
    }
}

Answer 1

查询（过滤，分组，总结等）时，请尝试使用 Linq < / em>

using System.Linq; using System.IO; ... // Our initial data var data = File .ReadLines(path1) .Skip(1) // Skip 1st record (header) .Where(line => !string.IsNullOrWhiteSpace(line)) // remove empty lines, if any .Select(line => line.Split('|')) // split each line by | .Select(items => new { Raw = string.Join("|", items), // Raw data as it is in the file Date = items[0].Trim(), ID = items[1].Trim(), Folder = items[2].Trim(), Doc = items[3].Trim(), FileName = items[4].Trim(), NoOfAct = items[5].Trim(), }); // Now, it's quite easy to represent the data as we want. // And we want to *group by* `Folder` and `ID`: just one GroupBy operation var result = data .GroupBy(item => new { ID = item.ID, Folder = item.Folder}) .Select(chunk => $"File {chunk.Key.Folder + "_" + chunk.Key.ID}.txt :\r\n {string.Join(Environment.NewLine + " ", chunk.Select(item => item.Raw))}"); foreach (var record in result) Console.WriteLine(record);

您会看到类似这样的内容：

File: ABC.20181101.CGLOG_1.txt : 20181024 |1 |ABC.20181101.CGLOG |test |xxxx |12 File: CDE.20181013.CGLOG_2.txt : 20181024 |2 |CDE.20181013.CGLOG |home |XyyX |2 ...

编辑：在您的 actual 问题中，让我们创建filesToWrite查询而不是result（我们已用于演示）{p >
var filesToWrite = data .GroupBy(item => new { ID = item.ID, Folder = item.Folder }) .Select(chunk => new { FileName = Path.Combine( @"F:\Work\Outcome", //TODO: put the desired directory here chunk.Key.Folder + "_" + chunk.Key.ID + ".txt"), Lines = chunk.Select(item => item.Raw) }); foreach (var file in filesToWrite) { // Let's create the directory if it doesn't exist Directory.CreateDirectory(Path.GetDirectoryName(file.FileName)); File.WriteAllLines(file.FileName, file.Lines); }

Answer 2

由于文件夹是您想要的，因此您在检查文件名时是否要检查文件名是否包含所需的字符串。

string[] lines = File.ReadAllLines(path1);
// Start at line number 2 because there is a header
for (int i = 1; i < lines.Length; i++)
{
    // 2 ways to do this:
    if (lines[i].Contains("%ABC%"))
    {
        // Copy it where you want
    }

    // or a more structured way:
    if (lines[i].Split('|')[2].Contains("ABC"))
    {
        // Copy it where you want
    }
}

从文本文件中查找行，然后使用c＃将其复制到新的文本文件中

2 个答案: