C# .Net正则表达式用捕获组替换模式的重复出现
我有一个SQL脚本,如下所示:C# .Net正则表达式用捕获组替换模式的重复出现,c#,.net,regex,vb.net,C#,.net,Regex,Vb.net,我有一个SQL脚本,如下所示: DECLARE @MyVariable1 = 1 DECLARE @MyVariable1 = 10 DECLARE @MyVariable3 = 15 DECLARE @MyVariable2 = 20 DECLARE @MyVariable1 = 7 DECLARE @MyVariable2 = 4 DECLARE @MyVariable4 = 7 DECLARE @MyVariable2 = 4 当然,真正的脚本在中间有很多其他的东西,但是我想写一个给定上
DECLARE @MyVariable1 = 1
DECLARE @MyVariable1 = 10
DECLARE @MyVariable3 = 15
DECLARE @MyVariable2 = 20
DECLARE @MyVariable1 = 7
DECLARE @MyVariable2 = 4
DECLARE @MyVariable4 = 7
DECLARE @MyVariable2 = 4
当然,真正的脚本在中间有很多其他的东西,但是我想写一个给定上面输入的函数,输出这个:
DECLARE @MyVariable1 = 1
@MyVariable1 = 10
DECLARE @MyVariable3 = 15
DECLARE @MyVariable2 = 20
@MyVariable1 = 7
@MyVariable2 = 4
DECLARE @MyVariable4 = 7
@MyVariable2 = 4
基本上删除已声明变量的重复DECLARE
语句
我目前的解决方案是:
Private Function RemoveDuplicateDeclarations(commandText As String) As String
Dim lines = commandText.Split(New String() { vbCrLf }, StringSplitOptions.RemoveEmptyEntries)
Dim declarationRegex As New Regex("(\r|\n|\r\n) *DECLARE *(?<initialization>(?<varname>[^ ]*) *.*)" & vbCrLf , RegexOptions.Multiline Or RegexOptions.IgnoreCase)
Dim declaredVariables As New List(Of String)
Dim resultBuilder As New StringBuilder()
For Each line In lines
Dim matches = declarationRegex.Matches(line)
If matches.Count > 0 Then
Dim varname = matches(0).Groups("varname").Value
If declaredVariables.Contains(varname) Then
resultBuilder.AppendLine(declarationRegex.Replace(line, "${initialization}"))
Else
declaredVariables.Add(varname)
resultBuilder.AppendLine(line)
End If
Else
resultBuilder.AppendLine(line)
End If
Next
Return resultBuilder.ToString()
End Function
您可以使用一个简单的正则表达式来搜索行中重复的
@
前缀词,并且只保留循环中的第一个匹配项,直到没有匹配项为止
(?sm)(^DECLARE\s+(@\w+\b).*?)^DECLARE\s+\2
详细信息:
-启用多行和单线(DOTALL)模式(?sm)
-组1捕获:(^DECLARE\s+(@\w+\b)。*?)
-^DECLARE
在行首声明
-1个或多个空白符号\s+
-第2组捕获(@\w+\b)
和1+个单词字符,直到尾随单词边界@
-任何0+字符,尽可能少,直到第一次出现*?
-行开头的^DECLARE
子字符串DECLARE
-1+空格\s+
-对存储在组2中的值的反向引用\2
如果您喜欢linq解决方案:
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Text.RegularExpressions;
using System.IO;
namespace ConsoleApplication1
{
class Program
{
static void Main(string[] args)
{
string input =
"DECLARE @MyVariable1 = 1\n" +
"DECLARE @MyVariable1 = 10\n" +
"DECLARE @MyVariable3 = 15\n" +
"DECLARE @MyVariable2 = 20\n" +
"DECLARE @MyVariable1 = 7\n" +
"DECLARE @MyVariable2 = 4\n" +
"DECLARE @MyVariable4 = 7\n" +
"DECLARE @MyVariable2 = 4\n";
string pattern = @"@(?'name'[^\s]+)\s+=\s+(?'value'\d+)";
MatchCollection matches = Regex.Matches(input, pattern);
string[] lines = matches.Cast<Match>()
.Select((x, i) => new { name = x.Groups["name"].Value, value = x.Groups["value"].Value, index = i })
.GroupBy(x => x.name)
.Select(x => x.Select((y, i) => new {
index = y.index,
s = i == 0
? string.Format("DECLARE @{0} = {1}", x.Key, y.value)
: string.Format("@{0} = {1}", x.Key, y.value)
}))
.SelectMany(x => x)
.OrderBy(x => x.index)
.Select(x => x.s)
.ToArray();
foreach (string line in lines)
{
Console.WriteLine(line);
}
Console.ReadLine();
}
}
}
使用系统;
使用System.Collections.Generic;
使用System.Linq;
使用系统文本;
使用System.Text.RegularExpressions;
使用System.IO;
命名空间控制台应用程序1
{
班级计划
{
静态void Main(字符串[]参数)
{
字符串输入=
“声明@MyVariable1=1\n”+
“声明@MyVariable1=10\n”+
“声明@MyVariable3=15\n”+
“声明@MyVariable2=20\n”+
“声明@MyVariable1=7\n”+
“声明@MyVariable2=4\n”+
“声明@MyVariable4=7\n”+
“声明@MyVariable2=4\n”;
字符串模式=@“@(?'name'[^\s]+)\s+=\s+(?'value'\d+);
MatchCollection matches=Regex.matches(输入,模式);
字符串[]行=匹配的.Cast()
.Select((x,i)=>new{name=x.Groups[“name”]。Value,Value=x.Groups[“Value”]。Value,index=i})
.GroupBy(x=>x.name)
.Select(x=>x.Select((y,i)=>new{
索引=y.index,
s=i==0
?string.Format(“DECLARE@{0}={1}”,x.Key,y.value)
:string.Format(“@{0}={1}”,x.Key,y.value)
}))
.SelectMany(x=>x)
.OrderBy(x=>x.index)
.选择(x=>x.s)
.ToArray();
foreach(行中的字符串行)
{
控制台写入线(行);
}
Console.ReadLine();
}
}
}
您用C#和VB.NET标记了您的问题,但您的代码在VB.NET中。这是否意味着C#标记可以删除?可以,我标记了C#,因为我不介意是否有人想用C#回答,因为正则表达式在两种环境中的工作原理相同
Dim rx As Regex = New Regex("(?sm)(^DECLARE\s+(@\w+\b).*?)^DECLARE\s+\2")
Dim s As String = "DECLARE @MyVariable1 = 1" & vbCrLf & "DECLARE @MyVariable1 = 10" & vbCrLf & "DECLARE @MyVariable3 = 15" & vbCrLf & "DECLARE @MyVariable2 = 20" & vbCrLf & "DECLARE @MyVariable1 = 7" & vbCrLf & "DECLARE @MyVariable2 = 4" & vbCrLf & "DECLARE @MyVariable4 = 7" & vbCrLf & "DECLARE @MyVariable2 = 4"
Dim res As String
Dim tmp As String = s
res = rx.Replace(s, "$1$2")
While (String.Compare(tmp, res) <> 0)
tmp = res
res = rx.Replace(res, "$1$2")
End While
Console.WriteLine(res)
DECLARE @MyVariable1 = 1
@MyVariable1 = 10
DECLARE @MyVariable3 = 15
DECLARE @MyVariable2 = 20
@MyVariable1 = 7
@MyVariable2 = 4
DECLARE @MyVariable4 = 7
@MyVariable2 = 4
using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using System.Text.RegularExpressions;
using System.IO;
namespace ConsoleApplication1
{
class Program
{
static void Main(string[] args)
{
string input =
"DECLARE @MyVariable1 = 1\n" +
"DECLARE @MyVariable1 = 10\n" +
"DECLARE @MyVariable3 = 15\n" +
"DECLARE @MyVariable2 = 20\n" +
"DECLARE @MyVariable1 = 7\n" +
"DECLARE @MyVariable2 = 4\n" +
"DECLARE @MyVariable4 = 7\n" +
"DECLARE @MyVariable2 = 4\n";
string pattern = @"@(?'name'[^\s]+)\s+=\s+(?'value'\d+)";
MatchCollection matches = Regex.Matches(input, pattern);
string[] lines = matches.Cast<Match>()
.Select((x, i) => new { name = x.Groups["name"].Value, value = x.Groups["value"].Value, index = i })
.GroupBy(x => x.name)
.Select(x => x.Select((y, i) => new {
index = y.index,
s = i == 0
? string.Format("DECLARE @{0} = {1}", x.Key, y.value)
: string.Format("@{0} = {1}", x.Key, y.value)
}))
.SelectMany(x => x)
.OrderBy(x => x.index)
.Select(x => x.s)
.ToArray();
foreach (string line in lines)
{
Console.WriteLine(line);
}
Console.ReadLine();
}
}
}