[文本处理] 求助：批处理如何实现去除相似重复行

^(.{1,})(.{1,9}\r?\n)(\1.{1,9}\r?\n)+
复制代码

$1$2
复制代码

//&cls&dir /b *.txt|cscript -nologo -e:jscript "%~f0"&echo 文本连续行去重复，有4个以上连续字符串不同则保留，可以修改{3,}增加数量&pause&exit

function reStr(file){
    var f = fso.opentextfile(file, 1);
    str = f.ReadAll().replace(/^(.{1,})(.{3,})(.{1,}\r?\n)(.{1,}\2.{1,}\r?\n)+/mg, '$1$2$3')
	.replace(/^(.{1,})(.{3,})(.{1,}\r?\n)(.{1,}\2.{1,}\r?\n)+/mg, '$1$2$3')
	.replace(/^(.{1,})(.{3,})(.{1,}\r?\n)(.{1,}\2.{1,}\r?\n)+/mg, '$1$2$3');
    f.Close();
    var f = fso.opentextfile(file, 2);
    f.Write(str);
}
var fso = new ActiveXObject('Scripting.FileSystemObject');
while(!WScript.StdIn.AtEndOfStream)reStr(WScript.StdIn.ReadLine());
复制代码

1
12
123
1234
12345
123456
1234567
12345678
123456789
1234567890
复制代码

@echo off & cd /d "%~dp0"
setlocal enabledelayedexpansion
REM 文件设置
set "in=a.txt"
set "out=b.txt"
REM 阈值设置 >=
set "max=4" 
REM 比较并输出
(
	set "num=1"
	for /f "usebackq delims=" %%i in ("%in%") do (
		title 处理第!num!行:     %%i
		if not "!last_line!"=="" (
			REM 比较当前行与上一行
			call :GetMax "!last_line!" "%%i"
			REM 当前< echo last and set last
			if !#max_char! lss !max! echo !last! & set "last=%%i"   
			set "last_max_char=!#max_char!!"
		) else set "last=%%i"
		REM 保存当前行到上一行
		set "last_line=%%i" & set /a "num+=1"
	)
	REM 输出最后的last
	echo !last!
)>"%out%"
pause&exit

REM 函数,获取两个字符串最大相同字符个数,%#max_char%
:GetMax
set "#s1=%~1" & set "#s2=%~2" & set /a "#i=0,#max_char=0"
set "#s1=%#s1:"='%" & set "#s2=%#s2:"='%"
:L1
if "!#s1:~%#i%,1!"=="" goto :eof
set "#j=1"
:L2
if "%#last%"=="!#s1:~%#i%,%#j%!" ( set /a "#i+=1" & goto :L1 )
set "#last=!#s1:~%#i%,%#j%!"
if not "!#s2:%#last%=!"=="%#s2%" if %#max_char% lss %#j% set /a "#max_char=#j"
set /a "#j+=1" & goto :L2
复制代码