[文本处理] 批处理如何区分txt文件是utf8还是ansi编码？

@echo off
for /f "delims=" %%i in ('dir /b /a-d *.txt') do (
	coder -s -a gc -f "%%i"|find "ANSI" 1>nul && (
		>>new_ansi.txt type "%%i"
	)
	coder -s -a gc -f "%%i"|find "UTF-8" 1>nul && (
		>>new_utf-8.txt type "%%i"
	)
)
coder -c ansi utf-8 -f "new_ansi.txt" >"new_utf-8_2.txt"
pause
复制代码

certutil "aaa.txt" |findstr /b /rc:"    00*  ef bb bf"
复制代码

@echo off&setlocal enabledelayedexpansion
echo.
for %%i in (*.txt) do (
certutil "%%~i" |findstr /b /m /rc:"    00*  ef bb bf" 1>nul 
if !errorlevel! equ 0 (echo "%%~ni    是utf8bom") else echo "%%~ni    不是utf8bom"
)
echo.&pause
复制代码

@echo off
set "param=-noprofile -executionpolicy bypass"
call:CodeName dir /b *.txt
call:Merge-txtfile
call:To-Utf8
type uft8-txt\tmp.txt
del uft8-txt\tmp.txt
pause
goto :eof

:CodeName
powershell %param% "md uft8-txt -force|out-null"
%*|powershell -noprofile -executionpolicy bypass "process{try{$CodeName=$Input|%%{if(Test-Path $input -PathType Leaf){[byte[]]$byte=gc -Encoding byte -ReadCount 4 -TotalCount 4 -Path $input;if( $byte[0] -eq 0xef -and $byte[1] -eq 0xbb -and $byte[2] -eq 0xbf ){'UTF8'}elseif($byte[0] -eq 0xfe -and $byte[1] -eq 0xff){'Unicode'}elseif($byte[0] -eq 0 -and $byte[1] -eq 0 -and $byte[2] -eq 0xfe -and $byte[3] -eq 0xff){'UTF32'}elseif($byte[0] -eq 0x2b -and $byte[1] -eq 0x2f -and $byte[2] -eq 0x76){'UTF7'}else{'ASCII'}}};if($CodeName -ne $null){('{0}={1}' -f $_,$CodeName)>>uft8-txt\tmp.txt}}catch{}}"
goto :eof


:Merge-txtfile
powershell %param% "gc uft8-txt\tmp.txt|%%{$s=$_ -split '=';gc $s[0]|ac "uft8-txt\New_$($s[1]).txt" -Encoding $s[1]}"
goto :eof

:To-Utf8
powershell %param% "gc uft8-txt\tmp.txt|%%{$s=$_ -split '=';gc $s[0]|out-file "uft8-txt\New_$($s[1])_$($s[0])" -Encoding utf8}"
goto :eof
复制代码