按空间拆分字符串,限制拆分C#

时间:2014-11-11 06:54:46

标签: c# regex split

示例输入

1   0.000000 10.19.20.105 -> 74.125.236.200 ICMP 74 Echo (ping) request  id=0x000a, seq=51187/62407, ttl=128
6   0.097977 74.125.236.194 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62844/31989, ttl=57 (request in 2)
7   0.131456 74.125.236.198 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62845/32245, ttl=57 (request in 3)
8   0.143539 74.125.236.196 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62847/32757, ttl=57 (request in 5)
9   0.160567 74.125.236.192 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62846/32501, ttl=57 (request in 4)
10   0.177972 10.19.20.172 -> 10.19.20.255 NBNS 92 Name query NB INDERPAL-PC<1c>
11   0.270418 10.19.20.105 -> 74.125.236.194 ICMP 74 Echo (ping) request  id=0x000b, seq=62848/33013, ttl=128
12   0.318404 10.19.20.105 -> 74.125.236.194 ICMP 74 Echo (ping) request  id=0x000b, seq=62849/33269, ttl=128
13   0.330236 74.125.236.194 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62848/33013, ttl=57 (request in 11)
14   0.376039 74.125.236.194 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62849/33269, ttl=57 (request in 12)
17   0.397384 10.19.20.105 -> 74.125.236.195 ICMP 74 Echo (ping) request  id=0x000b, seq=62852/34037, ttl=128
18   0.438108 74.125.236.200 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62850/33525, ttl=57 (request in 15)
19   0.444489 10.19.20.105 -> 74.125.236.196 ICMP 74 Echo (ping) request  id=0x000b, seq=62853/34293, ttl=128
21   0.463515 74.125.236.195 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62852/34037, ttl=57 (request in 17)
22   0.475425 10.19.20.105 -> 74.125.236.197 ICMP 74 Echo (ping) request  id=0x000b, seq=62854/34549, ttl=128
25   0.522472 74.125.236.197 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62854/34549, ttl=57 (request in 22)
26   0.535794 Giga-Byt_5d:06:ac -> Broadcast    ARP 60 Who has 10.19.20.74?  Tell 10.19.20.94
27   0.537735 Giga-Byt_a0:ad:23 -> Broadcast    ARP 60 Who has 10.19.20.94?  Tell 10.19.20.74
28   0.550321 10.19.20.105 -> 74.125.200.95 TCP 55 58240→80 [ACK] Seq=1 Ack=1 Win=16402 Len=1
29   0.574957 JetwayIn_a0:b1:a2 -> Broadcast    ARP 60 Who has 10.19.20.180?  Tell 10.19.20.172
30   0.584448 74.125.236.195 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62855/34805, ttl=57 (request in 24)


public class DataGridClass
    {
        public int SerialNumber { get; set; }
        public string Time { get; set; }
        public string DestinationIP { get; set; }
        public string SourceIP { get; set; }
        public string Protocol { get; set; }
        public int Length { get; set; }
        public string Info { get; set; }
    }

所需输出

SerialNumber = 1
Time = "0.000000"
DestinationIP = "10.19.20.105"
SourceIP = "74.125.236.200"
Protocol = "ICMP"
Length = 74
Info = "Echo (ping) request  id=0x000a, seq=51187/62407, ttl=128"

我无法用空格分割,因为字符串不一致,其次白色空间的数量可能增加或减少

提前致谢

更新

26,27与其他人不同

4 个答案:

答案 0 :(得分:1)

你可以使用正则表达式。这似乎适用于您的数据 注意 - 如果Dot-net支持它,请使用水平标签\h+代替下面的所有\s+

 #  @"(?m)^(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(\S+)\s+(.*)"

 (?m)
 ^ 
 ( \S+ )            # (1), Serial Number
 \s+ 
 ( \S+ )            # (2), Time
 \s+ 
 ( \S+ )            # (3), Destination IP
 \s+ 
 ( \S+ )            # (4), ->
 \s+ 
 ( \S+ )            # (5), Source IP
 \s+ 
 ( \S+ )            # (6), Protocol
 \s+ 
 ( \S+ )            # (7), Length
 \s+ 
 ( .* )             # (8), Info

第1,26,27行的输出样本

 **  Grp 0 -  ( pos 0 , len 108 ) 
1   0.000000 10.19.20.105 -> 74.125.236.200 ICMP 74 Echo (ping) request  id=0x000a, seq=51187/62407, ttl=128  
 **  Grp 1 -  ( pos 0 , len 1 ) 
1  
 **  Grp 2 -  ( pos 4 , len 8 ) 
0.000000  
 **  Grp 3 -  ( pos 13 , len 12 ) 
10.19.20.105  
 **  Grp 4 -  ( pos 26 , len 2 ) 
->  
 **  Grp 5 -  ( pos 29 , len 14 ) 
74.125.236.200  
 **  Grp 6 -  ( pos 44 , len 4 ) 
ICMP  
 **  Grp 7 -  ( pos 49 , len 2 ) 
74  
 **  Grp 8 -  ( pos 52 , len 56 ) 
Echo (ping) request  id=0x000a, seq=51187/62407, ttl=128  

--------------------------------

 **  Grp 0 -  ( pos 1873 , len 93 ) 
26   0.535794 Giga-Byt_5d:06:ac -> Broadcast    ARP 60 Who has 10.19.20.74?  Tell 10.19.20.94  
 **  Grp 1 -  ( pos 1873 , len 2 ) 
26  
 **  Grp 2 -  ( pos 1878 , len 8 ) 
0.535794  
 **  Grp 3 -  ( pos 1887 , len 17 ) 
Giga-Byt_5d:06:ac  
 **  Grp 4 -  ( pos 1905 , len 2 ) 
->  
 **  Grp 5 -  ( pos 1908 , len 9 ) 
Broadcast  
 **  Grp 6 -  ( pos 1921 , len 3 ) 
ARP  
 **  Grp 7 -  ( pos 1925 , len 2 ) 
60  
 **  Grp 8 -  ( pos 1928 , len 38 ) 
Who has 10.19.20.74?  Tell 10.19.20.94  

----------------------------

 **  Grp 0 -  ( pos 1968 , len 93 ) 
27   0.537735 Giga-Byt_a0:ad:23 -> Broadcast    ARP 60 Who has 10.19.20.94?  Tell 10.19.20.74  
 **  Grp 1 -  ( pos 1968 , len 2 ) 
27  
 **  Grp 2 -  ( pos 1973 , len 8 ) 
0.537735  
 **  Grp 3 -  ( pos 1982 , len 17 ) 
Giga-Byt_a0:ad:23  
 **  Grp 4 -  ( pos 2000 , len 2 ) 
->  
 **  Grp 5 -  ( pos 2003 , len 9 ) 
Broadcast  
 **  Grp 6 -  ( pos 2016 , len 3 ) 
ARP  
 **  Grp 7 -  ( pos 2020 , len 2 ) 
60  
 **  Grp 8 -  ( pos 2023 , len 38 ) 
Who has 10.19.20.94?  Tell 10.19.20.74  

答案 1 :(得分:1)

试试这个:

(^\d*) SerialNumber = 1
(\s\d*[.]\d*\s) Time = "0.000000"

\b\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}\b - [0] - first IP, [1] - second IP 

DestinationIP = "10.19.20.105"
SourceIP = "74.125.236.200"

([A-Z]{2,}) Protocol = "ICMP"
(\s\d{1,}\s) Length = 74
((Echo).*) Info = "Echo (ping) request  id=0x000a, seq=51187/62407, ttl=128"

答案 2 :(得分:0)

要解决问题,如果空格不一致,请使用:

var items = test.Split(new char[] {' '}, StringSplitOptions.RemoveEmptyEntries);

幸运的是,您的所有数据都是一致的顺序,并且不包含数据中的随机空格。因此,考虑到上面拆分所采取的项目,您应该发现以下内容总是正确分配:

var dataGrid = new DataGridClass();

dataGrid.SerialNumber = int.Parse(items[0]);
dataGrid.Time = items[1];
dataGrid.SourceIP = items[2];
dataGrid.DestinationIP = items[4]; // Not a typo, we have to skip the ->
dataGrid.Protocol = items[5];
dataGrid.Length = int.Parse(items[6]);
datagrid.Info = string.Join(" ", items.Skip(7));

我试图使用Info聪明,但如果它不像我想的那样工作,请随意简单地说:

for (int i = 7; i < items.Length; ++i)
{
    dataGrid.Info += items[i] + " ";
}

答案 3 :(得分:0)

我也会使用正则表达式

^(\ d +)\ S +(\ S +)\ S +(\ S +)\ S * - &GT;(。*)\ S *(\ S +)\ S +(\ S +)\ S +(\ d +)$

开始(序列号)一个或多个空格(时间)一个或多个空格(目的地IP)零或更多空格 - &gt;零个或多个空格(源IP)一个或多个空格(协议)一个或多个空格(长度)一个或多个空格(信息)结束

class Program
{
    static void Main(string[] args)
    {
        string []inputs = {@"1   0.000000 10.19.20.105 -> 74.125.236.200 ICMP 74 Echo (ping) request  id=0x000a, seq=51187/62407, ttl=128",
                            @"6   0.097977 74.125.236.194 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62844/31989, ttl=57 (request in 2)",
                            @"7   0.131456 74.125.236.198 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62845/32245, ttl=57 (request in 3)",
                            @"8   0.143539 74.125.236.196 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62847/32757, ttl=57 (request in 5)",
                            @"9   0.160567 74.125.236.192 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62846/32501, ttl=57 (request in 4)",
                            @"10   0.177972 10.19.20.172 -> 10.19.20.255 NBNS 92 Name query NB INDERPAL-PC<1c>",
                            @"11   0.270418 10.19.20.105 -> 74.125.236.194 ICMP 74 Echo (ping) request  id=0x000b, seq=62848/33013, ttl=128",
                            @"12   0.318404 10.19.20.105 -> 74.125.236.194 ICMP 74 Echo (ping) request  id=0x000b, seq=62849/33269, ttl=128",
                            @"13   0.330236 74.125.236.194 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62848/33013, ttl=57 (request in 11)",
                            @"14   0.376039 74.125.236.194 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62849/33269, ttl=57 (request in 12)",
                            @"17   0.397384 10.19.20.105 -> 74.125.236.195 ICMP 74 Echo (ping) request  id=0x000b, seq=62852/34037, ttl=128",
                            @"18   0.438108 74.125.236.200 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62850/33525, ttl=57 (request in 15)",
                            @"19   0.444489 10.19.20.105 -> 74.125.236.196 ICMP 74 Echo (ping) request  id=0x000b, seq=62853/34293, ttl=128",
                            @"21   0.463515 74.125.236.195 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62852/34037, ttl=57 (request in 17)",
                            @"22   0.475425 10.19.20.105 -> 74.125.236.197 ICMP 74 Echo (ping) request  id=0x000b, seq=62854/34549, ttl=128",
                            @"25   0.522472 74.125.236.197 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62854/34549, ttl=57 (request in 22)",
                            @"26   0.535794 Giga-Byt_5d:06:ac -> Broadcast    ARP 60 Who has 10.19.20.74?  Tell 10.19.20.94",
                            @"27   0.537735 Giga-Byt_a0:ad:23 -> Broadcast    ARP 60 Who has 10.19.20.94?  Tell 10.19.20.74",
                            @"28   0.550321 10.19.20.105 -> 74.125.200.95 TCP 55 58240→80 [ACK] Seq=1 Ack=1 Win=16402 Len=1",
                            @"29   0.574957 JetwayIn_a0:b1:a2 -> Broadcast    ARP 60 Who has 10.19.20.180?  Tell 10.19.20.172",
                            @"30   0.584448 74.125.236.195 -> 10.19.20.105 ICMP 74 Echo (ping) reply    id=0x000b, seq=62855/34805, ttl=57 (request in 24)",
                        };

        List<DataGridClass> data = new List<DataGridClass>();
        Match match;
        foreach (var item in inputs)
        {
            match = Regex.Match(item, @"^(\d+)\s+(\S+)\s+(\S+)\s*->\s*(\S+)\s+(\S+)\s+(\d+)(.*)$");
            if (match.Success )
            {
                data.Add(new DataGridClass { 
                    SerialNumber = Convert.ToInt32(match.Groups[1].Value),
                    Time = match.Groups[2].Value,
                    DestinationIP = match.Groups[3].Value,
                    SourceIP = match.Groups[4].Value,
                    Protocol = match.Groups[5].Value,
                    Length = Convert.ToInt32(match.Groups[6].Value),
                    Info = match.Groups[7].Value,
                });
            }
        }

        if (data.Count > 0)
        {
            foreach (var item in data)
            {
                Console.WriteLine(String.Format("SN: {0}, T: {1}, DIP: {2}, SIP: {3}, P: {4}, L: {5}, I: {6}",
                    item.SerialNumber, item.Time, item.DestinationIP, item.SourceIP, item.Protocol, item.Length, item.Info));
            }
        }
        Console.ReadLine();
    }
}

public class DataGridClass
{
    public int SerialNumber { get; set; }
    public string Time { get; set; }
    public string DestinationIP { get; set; }
    public string SourceIP { get; set; }
    public string Protocol { get; set; }
    public int Length { get; set; }
    public string Info { get; set; }
}